DARPA SBIR DPA26BZ06-DV028: TRIAGE-X, Autonomous Casualty Triage and Treatment in Chemically Contaminated Mass Casualty Events
Quick Answer
DPA26BZ06-DV028 is a DARPA SBIR Direct to Phase II topic under the DoW 2026 SBIR Broad Agency Announcement, Release 6. DARPA wants autonomous medical triage systems that recognize chemical toxidromes and physically deliver the corresponding antidote or life-saving intervention. Not recommend it. Deliver it. The award is $1,500,000 over 24 months with a $500,000 option over 6 months. The topic opens September 23, 2026 and closes October 21, 2026 through the Defense SBIR/STTR Innovation Portal.
The operational logic is the reason this exists. When a mass casualty incident occurs inside a chemically contaminated area, responders cannot enter until the threat is assessed and characterized. To be safe they must don protective equipment first, which delays initial assessment, triage, and treatment. That equipment then imposes a physiological and functional penalty: slower movement, higher energy expenditure, heat stress, impaired respiration, and reduced manual dexterity, all of which further impede the ability to perform life-saving interventions. Meanwhile effective stabilization occurs in the cold zone, after casualties have been decontaminated, compounding the delay to evacuation and definitive care. An autonomous system that performs initial triage and treatment in the hot zone means responders either avoid entry entirely or gain time to don protective equipment.
The feasibility bar is high and specific. DARPA states that Phase I work is expected to have been completed before award, and lists concrete capabilities your existing prototype must already demonstrate, including autonomously finding and localizing casualties to within 2 meters, standoff vital signs assessment, and operating at scale across at least 20 casualties in a single scenario, all supported by a written technical description or published report with data and video.
Topic At a Glance
Topic number: DPA26BZ06-DV028
Title: TRIAGE-X: Autonomous Casualty Triage and Treatment in Chemically Contaminated Mass Casualty Events
Agency: Defense Advanced Research Projects Agency (DARPA)
Solicitation: DoW 2026 Small Business Innovation Research Broad Agency Announcement, Release 6, DARPA Proposal Submission Instructions
Program type: Direct to Phase II (DP2)
Technical volume format: White Paper and Slide Deck. The white paper shall not exceed 20 pages and the slide deck shall not exceed 15 slides
Base award: $1,500,000
Base period of performance: 24 months
Option: $500,000 over 6 months
Component Technology Priority Areas: Advanced Computing and Software; Biotechnology; Human-Machine Interfaces; Integrated Sensing and Cyber; Trusted AI and Autonomy
Projected CMMC level requirement: Level 2 (Self)
Export control status: no topic-level ITAR or EAR restriction paragraph appears on this topic
Minimum deliverable: a demonstrated prototype that detects at least two representative chemical toxidromes and applies appropriate initial treatments following human-in-the-loop treatment approval
Out of scope: identification of the specific chemical agent, and chemical-specific sensors
Technical and Business Assistance: up to $25,000 per Phase II project, in addition to the cost ceiling
Topic Q&A: DSIP Topic Q&A is not available for DARPA topics. Technical questions go to SBIR_BAA@darpa.mil by October 14, 2026
Topic open date: September 23, 2026
Proposal deadline: October 21, 2026. DARPA will not accept late proposals
Submission portal: DSIP at dodsbirsttr.mil
Keywords: medical triage, mass casualty incidents, autonomous systems, robotics, medical countermeasures, chemical warfare injuries
The Feasibility Bar, Which Is the First Thing to Check
DARPA states that Phase I work is expected to have been completed before award. Proposers must submit evidence that their existing prototype can do six things.
Autonomously find and localize casualties and report their location to within 2 meters.
Assess trauma patterns and assign a trauma triage category.
Perform accurate standoff vital-signs assessment, including at minimum heart rate and respiratory rate.
Operate at scale, defined as at least 20 casualties in a single scenario, performing assessment in under 90 seconds for each casualty, and surveying a 30,000 square foot area without a battery change.
Operate across diverse, realistic environments: indoor and outdoor, daytime and nighttime, ideally but not required in adverse weather conditions such as rain and smoke.
Produce a human-interpretable output through a graphical interface that conveys casualty locations and priorities of care.
Plus a system requirement: the system must be portable, with all components easily transported by a vehicle or drone.
How the evidence must be presented
Capability demonstration: a written technical description or published report supported by data and videos demonstrating the prototype performing the capabilities above in the stated environments are required, provided via link.
Note "provided via link." Your videos are delivered as links rather than embedded files, which means hosting them somewhere durable and accessible to Government reviewers. Check the links work from outside your network and will stay live through the evaluation period, which runs up to 90 days past October 21.
What this bar actually screens for
Read the list together and the intended applicant becomes clear: a team that already fields an autonomous casualty search and triage system. The 2 meter localization, the sub-90-second per-casualty assessment, the 20-casualty scale, and the 30,000 square foot single-battery survey are all performance numbers from a working platform, not projections.
DARPA says so directly elsewhere in the topic. The DARPA Triage Challenge has demonstrated that autonomous air and ground systems, using standoff sensors, can locate casualties, characterize injury patterns, and support triage prioritization in realistic mass casualty incident conditions. Using DARPA Triage Challenge triage support capabilities as a starting point, this solicitation aims to extend capabilities to operating in chemically hazardous environments where injury patterns have distinct signatures or toxidromes.
If you competed in or built toward the DARPA Triage Challenge, this topic is written for you. If you have not, the honest question is whether you can document all six capabilities with data and video before October 21.
What DARPA Is Actually Looking For
The objective
Develop and demonstrate capability with autonomous medical triage systems to recognize chemical toxidromes and physically deliver the corresponding antidote or life-saving intervention.
The operational problem
DARPA seeks innovative approaches to autonomous chemical, biological, radioactive, and nuclear triage that measurably improve casualty survival and increase the effective capacity of a medical response during CBRN disasters.
Early situational awareness and timely treatment is a matter of life and death in battlefield and disaster medical triage. Responder vulnerability in hazardous environments caused by CBRN attacks adds significant difficulty to the medical response.
When a mass casualty incident occurs within a chemically contaminated area, the medical response is hindered by uncertainty while the threat is assessed and characterized. To ensure safety of the responders, they must don protective equipment before entry, delaying initial assessment, triage, and treatment with life-saving interventions.
Personal protective equipment also imposes a physiological and functional penalty on responders resulting in slower movement, higher energy expenditure, heat stress, impaired respiration, and reduced manual dexterity. These penalties further impede responders' ability to perform life-saving interventions.
Effective stabilization occurs in the cold zone after casualties have been decontaminated, compounding the delay to evacuation and definitive care.
Success here extends proven autonomous triage into one of the most challenging settings where human entry is dangerous and delayed, and where early antidote delivery most directly determines casualty survival.
What the system must do
Proposed systems should be able to locate and assess casualties for traumatic injuries and chemical toxidromes, generate triage recommendations, and deliver appropriate initial treatments to reverse, stabilize, or prevent the toxic effects of chemicals.
Solutions should be designed for realistic operational use in difficult terrain under challenging environmental conditions.
What DARPA deliberately does not prescribe
DARPA does not prescribe a specific platform, sensor suite, or level of autonomy. Offerors are encouraged to propose the human-machine teaming arrangement that best improves decision quality and casualty outcomes, and to define how their system fails safely when conditions exceed its competence.
That second clause is unusual and important. Defining how your system fails safely when conditions exceed its competence is a stated requirement. Autonomous systems administering medication in a contaminated environment need explicit competence boundaries and safe behavior at those boundaries. Address it directly rather than treating it as a risk paragraph.
Approaches should be realistic in scope, repurposed within the period of performance, and grounded in how CBRN mass casualty response actually unfolds.
At minimum, the effort shall deliver a demonstrated prototype that detects at least two representative chemical toxidromes and applies appropriate initial treatments for the assessed toxidrome following human-in-the-loop treatment approval.
Two toxidromes minimum. Treatment decisions always made by humans. Those two constraints bound the program.
Agent identification is explicitly out of scope
Performers shall develop the capability to assess and treat at least two chemical agent categories from the topic's toxidrome table. Agent detection is out of scope for this effort.
The requirements table repeats it: identification of the specific chemical agent is out of scope, and chemical-specific sensors are also out of scope.
This is a significant scoping decision and it should shape your architecture. You are not building a chemical detector. You are building a system that reads the casualty's physical presentation, the toxidrome, and infers the likely agent category from clinical signs. That is a medical inference problem from observable physiology and behavior, not a chemistry problem. Proposals that lean on chemical sensing have misread the topic.
The Toxidromes and Treatments
The topic provides three tables. Table 1 defines the target toxidromes, representative agents, physical presentation, and anticipated treatment to demonstrate. Table 2 defines how those toxidromes will be simulated on mannikins for demonstration. Table 3 defines the required technical capabilities.
Table 1, the five toxidrome categories
Cholinergic, or nerve-agent, syndrome. Representative agents: sarin, VX, Novichok, organophosphates. Physical presentation: DUMBBELS, meaning diarrhea, urination, miosis or constricted pupils, muscle weakness, bronchospasm, bronchorrhea, bradycardia or decreased heart rate, emesis, lacrimation, salivation and sweating. Anticipated treatment: intramuscular pharmaceutical delivery of simulated antidote, atropine and pralidoxime, plus airway management.
Blood-agent, or cyanide, syndrome. Representative agents: hydrogen cyanide, cyanogen chloride. Physical presentation: rapid collapse, gasping, tachypnea or fast respiratory rate progressing to apnea or no breathing, altered mental status, seizures, cardiovascular instability with low blood pressure and fast heart rate, skin flushing, central cyanosis, dilated pupils. Anticipated treatment: IV or IO pharmaceutical delivery, such as a cyanokit, plus airway management.
Pulmonary or choking-agent syndrome. Representative agents: chlorine, phosgene. Physical presentation: cough, dyspnea or difficulty breathing, wheezing, stridor, eye and airway irritation, respiratory distress, delayed pulmonary edema. Anticipated treatment: delivery of bronchodilators plus airway management.
Vesicant or blister-agent syndrome. Representative agent: sulfur mustard. Physical presentation: blistering skin burns, airway irritation, pain. Anticipated treatment: skin decontamination with removal of substance from exposed skin and clothing, and washing skin or using decontamination cloths, plus airway management.
Opioid or respiratory-depressant syndrome. Representative agent: fentanyl-type incapacitants. Physical presentation: pinpoint pupils, respiratory depression progressing to apnea, decreased consciousness. Anticipated treatment: intranasal or intramuscular naloxone plus airway management.
Two footnotes to Table 1 matter. Airway management includes providing supplemental oxygen by mask AND escalating to either non-invasive, meaning bag-valve mask or mechanical, or invasive, meaning endotracheal intubation or surgical airway, ventilation. And the cyanide treatment note specifies that IV or IO delivery includes autonomous placement of an intravenous or intraosseous catheter.
That last item is worth pausing on. Autonomous placement of an IV or IO catheter is a substantially harder robotic task than an intramuscular injection. If you select the blood-agent category as one of your two, you are committing to autonomous vascular or intraosseous access. Choosing cholinergic and opioid syndromes, both of which use intramuscular or intranasal delivery, is a materially easier engineering path. Choose deliberately and justify the choice.
Table 2, simulated presentations on mannikins
Performers will demonstrate their platform's ability to recognize simulated toxidromes in silico, meaning computer-based simulation, and on high-fidelity mannikins with the simulated toxidrome presentations outlined in Table 2.
The simulated cues are concrete and tell you exactly what your perception system must detect. For cholinergic syndrome: damp or wet clothing around the groin area and on the ground, constricted pupils, coughing sounds, rapid breathing at a rate greater than 30, slow palpable pulses at the wrist and groin at a rate under 40, emesis from the mouth with head turned and vomit on the side of the face and on the ground, and damp "skin" sprayed on with liquid.
For blood-agent syndrome: coughing sounds, rapid breathing greater than 30, altered mental status or confusion shown as mumbling words and not responding verbally to instructions, flushed red-appearing skin, dilated pupils.
For pulmonary syndrome: coughing sounds, rapid breathing greater than 30, red or irritated eyes with scleral injection, wheezing on auscultation of lung sounds, cyanosis around the lips.
For vesicant syndrome: gelatin on skin, skin blisters and burns, coughing sounds, rapid breathing greater than 20.
For opioid syndrome: constricted pupils, slow breathing at a rate under 10, unconscious and non-responsive.
Read that list as your sensing requirements specification. Pupillometry, respiratory rate, pulse palpation or standoff equivalent, auscultation, skin color and moisture assessment, blister detection, verbal responsiveness testing, and vomit detection. Several of these require close approach or contact, not just standoff sensing, which interacts with the mobility and manipulation design.
Table 3, required technical capabilities
Casualty Assessment. Locate casualty and report clinical signs including hemorrhage, respiratory distress, mental status, pain, emesis, injuries and injury location. Evaluate casualties for chemical toxidromes and assign a probable target agent category from Table 1. Assign triage category, urgent or non-urgent. Identification of the specific chemical agent is out of scope, and chemical-specific sensors are also out of scope.
Intervention Delivery. The platform must physically administer treatment appropriate to the chosen toxidrome according to Table 1 on a mannikin, and this is marked as required on a mannikin. Final demonstration requires the system payload and automation to administer treatment to at least 5 casualties in succession without battery changes or re-supply, also marked as required on a mannikin.
That five-casualty-in-succession requirement without battery change or resupply is a hard payload and endurance constraint. It means carrying five doses and the power to deliver them, and it interacts with the 30,000 square foot survey requirement from the feasibility bar.
Platform, Environment, and Autonomy. Platform-agnostic: autonomous UAV and UGV, and the performer may choose the sensor suite excluding chemical-specific sensors. System must demonstrate safe physical interaction with casualties represented by high-fidelity mannikins. A single robust platform must operate across and transition between realistic environments, meaning difficult terrain, inside and outside of buildings, and potentially subterranean settings, and this is marked as required over real terrain. Dedicated single-environment platforms are not sought.
That last sentence rules out a design optimized for one setting. One platform, multiple environments, including transitions between them.
End of Program Demonstration. Detection and assessment may be validated computationally through assessment of a test set of images and videos showing injuries and clinical signs such as respiratory distress, pupillary changes, salivation, sweating, skin changes and blisters. Intervention delivery on multiple casualties must be validated by physical demonstration, marked as required on a mannikin and over real terrain. The essential program output is a validated prototype.
Note the split: perception can be validated computationally against a test set, but intervention delivery must be physically demonstrated. That is a sensible and demanding division, and it means your budget needs real robotic manipulation development and mannikin testing, not just a vision pipeline.
Phase II
Building on the feasibility demonstrated in the documentation above, the Phase II effort will extend their qualified baseline system to assess and treat chemical toxidromes.
In this effort, performers will develop, integrate, and validate a prototype autonomous chemical casualty triage system and demonstrate it in a relevant environment.
The system shall identify casualties, assess them for life threatening and other traumatic injuries, assess casualties for chemical toxidromes, and provide relevant physical treatments.
Requirements: performers shall develop the capability to assess and treat at least two chemical agent categories from Table 1. Agent detection is out of scope for this effort. Treatment recommendations and options for each casualty shall be presented through a graphical interface to responders. Treatment decisions will always be made by humans.
The human-in-the-loop requirement is stated three separate times in the topic. Whatever autonomy you propose for search, assessment, and navigation, the treatment decision itself is a human decision presented through an interface. Design and describe that interface carefully, because it is the point where an autonomous system hands a life-or-death decision to a person who may be outside the hot zone.
Phase III Dual Use
Military: autonomous triage and toxidrome-directed treatment in chemically contaminated, battlefield environments protects medics from entry and prolongs casualty survival until human care is possible.
Civilian: similarly, autonomous systems capable of assessing and delivering life sustaining treatments during disaster responses, industrial chemical accidents, hazmat operations, and chemical terror attacks in which fire and EMS response will be delayed provides additional safety for responders and a survival advantage for casualties during public-health emergencies. The autonomous system will perform initial triage and treatment in the hot zone so that responders either avoid entry entirely or gain time to don protective equipment.
The civilian market here is concrete and reachable. Industrial chemical facilities, hazmat response teams, fire departments in petrochemical corridors, and emergency management agencies all face the same hot-zone entry delay. Opioid and fentanyl-related mass exposure incidents are a further civilian use case that maps directly onto one of the five toxidrome categories.
Funding, Cost Structure, and DARPA Mechanics
The award
$1,500,000 over a 24 month base, plus a $500,000 option over 6 months, for $2,000,000 across 30 months if the option is exercised.
The resources made available for each topic will depend on the quality of the proposals received and the availability of funds. The Government reserves the right to award all, some, one, or none of the options based on available funding and the performer's technical performance.
Contract type, which you must elect
DARPA may award FAR-based contracts, firm-fixed-price or cost-plus reimbursement, or Other Transactions for Prototype under the authority of 10 U.S.C. 4021, subject to approval of the Contracting Officer or Agreements Officer respectively. Proposers must state their requested contract type in their proposal.
Cost-plus reimbursement requires including your Defense Contract Management Agency Final Determination Letter showing approval of your accounting system. An Other Transaction for Prototype requires including a completed OT using the Model OT for Prototype from the DARPA Small Business site, plus completed OT Certifications, both loaded in Volume 5, with at minimum the color-coded areas completed and redlines with explanations for any article you wish to negotiate. Firm-fixed-price requires no additional action.
Templates are mandatory
Templates for Volume 2 Technical Volume and Volume 3 Cost Volume are provided as attachments on the DARPA Small Business website. Use of the DARPA Cost Proposal template is mandatory.
Technical and Business Assistance
Phase II awardees may request up to $25,000 per Phase II project. TABA funding is in addition to the cost ceilings and is not subject to profit or fee. Requests will be reviewed by the respective contracting office or specialist at time of award.
For this topic, regulatory strategy is worth considering, since a system that autonomously administers medication will eventually face a device and drug-delivery regulatory pathway, and intellectual property protections given the robotics and algorithm content.
Questions and the FAQ
DSIP Topic Q&A will not be available for these DARPA topics. Technical questions must be submitted by October 14, 2026, by email to SBIR_BAA@darpa.mil with the topic number in the subject line, including the name, email address, and telephone number of a point of contact. Questions submitted within seven calendar days of the proposal due date may not be answered. DARPA posts a consolidated Frequently Asked Questions document under the topic number summary on its Small Business site, updated on an ongoing basis until one week prior to the proposal due date.
DARPA will not accept late proposals.
Classification, marking, and registrations
All proposals are required to be UNCLASSIFIED or CUI. Do not include any classified information in your proposal submission. Do not include any proprietary information on the Proposal Coversheet in Volume 1.
Proposal titles, abstracts, anticipated benefits, and keywords of proposals selected for contract award will undergo a DARPA Policy and Security Review and are subject to revision or redaction by DARPA. Final approved versions may appear on the DoW SBIR/STTR awards website and the SBA's award website at sbir.gov/awards.
Proposers should ensure they have an accurate and active entity registration on SAM.gov. Those engaging in ITAR or CUI work for DARPA must have CMMC Level 2 certification, and the projected requirement for this topic is Level 2 with self-assessment. DARPA points to sprs.csd.disa.mil/nistsp.htm and notes Project Spectrum at projectspectrum.io as an assistance resource.
Venture capital, hedge fund, and private equity ownership
Proposers that are more than 50 percent owned by multiple venture capital operating companies, hedge funds, private equity firms, or any combination of these as set forth in 13 CFR 121.702 are eligible to submit proposals in response to DARPA topics advertised within this BAA. Three conditions apply: register with the SBA Company Registry Database before submitting; submit the Majority-Owned VCOC, HF, and PEF Certification, with the SBIR VC Certification available on the DARPA Small Business site, in Supporting Documents Volume 5; and immediately notify the Contracting Officer, register in the appropriate SBA database, and submit the required certification if you enter that ownership class after submitting but before receiving a funding agreement.
DARPA's permissive posture matters here, since autonomous robotics companies capable of clearing this feasibility bar are commonly venture-funded.
Evaluation and selection
All proposals will be evaluated in accordance with the evaluation criteria listed in the DoW SBIR Program BAA. DARPA will conduct an evaluation of each conforming proposal. Proposals that do not comply with the requirements detailed in this BAA and the research objectives of the corresponding topic are considered non-conforming and are therefore not evaluated nor considered for award.
Using the evaluation criteria, the Government will evaluate each proposal in its entirety, documenting the strengths and weaknesses relative to each evaluation criteria, and based on those will determine the proposal's overall selectability for funding. Proposals will not be evaluated against each other but on their own individual merit.
A selectable proposal is one where the strengths of the overall proposal outweigh its weaknesses, with no accumulated weaknesses that would require extensive negotiations or a resubmitted proposal. A non-selectable proposal is one where the strengths do not outweigh its weaknesses.
Proposing firms will be notified of selection or non-selection status within 90 calendar days of the closing date of the BAA. The Corporate Official indicated on the Proposal Cover Sheet will be notified by email. In accordance with the SBA SBIR/STTR Policy Directive, Appendix I, paragraph 4, subparagraph (d), DARPA will provide a technical evaluation narrative to the proposer for each proposal submitted in response to a topic. An informal feedback session may additionally be requested via email at sbir@darpa.mil, provided at the sole discretion of DARPA.
Company Commercialization Report information will not be considered by DARPA during proposal evaluations.
Protests regarding the selection decision should be submitted, as prescribed in FAR 33.106(b) and FAR 52.233-3, to DARPA Contracts Management Office, 675 N. Randolph Street, Arlington, VA 22203, by email to CMO_SBIRProtests@darpa.mil and sbir@darpa.mil.
Post-award support
DARPA provides Transition and Commercialization Support Program services to Phase II and DP2 awardees upon contract execution at no cost to awardees. Awardees may also be eligible for the Embedded Entrepreneurship Initiative, an invitation-only program at DARPA's sole discretion, typically no more than $310,000 per awardee over the duration of the award, supporting a Senior Commercialization Advisor relationship, investor working group connections, and hiring an embedded entrepreneur to execute a Go-to-Market strategy.
The References
Six, and the mix tells you what literacy DARPA expects: chemical casualty medicine plus its own prior program.
Dembek ZF, editor. Medical aspects of biological warfare. Government Printing Office; 2008.
Ramesh AC, Kumar S. Triage, monitoring, and treatment of mass casualty events involving chemical, biological, radiological, or nuclear agents. Pharmacy and Bioallied Sciences.
The DARPA Triage Challenge program summary, at darpa.mil, attachment dtc-challenge-program-summary.pdf dated 2026-05.
Keating B, Eide KL, Vaag JR, Lund-Kordahl I. Tactical Triage: Adapting Care and Decision-Making for High-Threat Environments.
U.S. Department of the Air Force (2021). Air force tactics, techniques, and procedures 3-42.32: Installation medical all hazards response, IMAHR.
Marrs TC. Toxicology of organophosphate nerve agents. Chemical warfare agents: toxicology and treatment. 2007.
The DARPA Triage Challenge program summary is the most operationally useful of these. It describes the baseline capability DARPA says this topic extends, and it will tell you what the agency already considers demonstrated. Read it before writing, and position your system relative to it explicitly.
The Marrs organophosphate toxicology chapter and the Dembek volume are the clinical grounding for toxidrome recognition and treatment. The AFTTP 3-42.32 Installation Medical All Hazards Response publication is the doctrine for how the Air Force actually organizes a chemical mass casualty response, which is where your system has to fit.
Timeline and What to Do When
The dates
Topic opens: September 23, 2026
Technical question deadline: October 14, 2026, to SBIR_BAA@darpa.mil with the topic number in the subject line
Proposal deadline: October 21, 2026. DARPA will not accept late proposals
Selection notification: within 90 calendar days of BAA close
Base period: 24 months from award
Option: 6 additional months if exercised
A working backward plan
Before September 23. Assess yourself against the six feasibility capabilities honestly, since Phase I work is expected to have been completed before award. Assemble the written technical description or published report with supporting data and videos, and host the videos at durable links accessible from outside your network. Download the mandatory DARPA Volume 2 and Volume 3 templates. Read the FAQ and keep rechecking it. Read the DARPA Triage Challenge program summary and position relative to it. Choose your two toxidrome categories, weighing the intramuscular and intranasal routes against the IV and IO route which requires autonomous catheter placement. Secure access to high-fidelity mannikins and a test environment covering difficult terrain, indoor and outdoor, and ideally subterranean transitions. Decide your contract type and prepare the corresponding documents. Confirm SAM registration and your CMMC Level 2 self-assessment in SPRS. If venture-backed, register with the SBA Company Registry and obtain the SBIR VC Certification.
September 23 through October 5. Draft the 20 page white paper and 15 slide deck. Structure around the toxidrome selection and the clinical inference from Table 2 cues, the intervention delivery mechanism, the platform and environment transitions, the human-in-the-loop treatment interface, and the fail-safe behavior when conditions exceed system competence. Use the slide deck for platform imagery, sensing geometry, and demonstration evidence, which is what slides do better than prose.
October 6 through October 14. Build the cost volume in the mandatory template across 24 months plus the 6 month option. Price mannikin acquisition or access, drug-delivery payload development, test range or facility access covering multiple environments, and the five-casualty-in-succession endurance testing.
October 15 through October 18. Assemble Volume 5 with contract-type documents and certifications, complete Volume 7 and the Volume 4 CCR, and run compliance: 20 page white paper, 15 slide deck, unclassified or CUI only, no proprietary information on the coversheet, mandatory cost template, working video links.
October 19 through October 20. Submit and certify in DSIP.
Frequently Asked Questions
What is DARPA SBIR topic DPA26BZ06-DV028?
DPA26BZ06-DV028 is a DARPA SBIR Direct to Phase II topic titled "TRIAGE-X: Autonomous Casualty Triage and Treatment in Chemically Contaminated Mass Casualty Events," released under the DoW 2026 SBIR Broad Agency Announcement, Release 6. The objective is to develop and demonstrate capability with autonomous medical triage systems to recognize chemical toxidromes and physically deliver the corresponding antidote or life-saving intervention.
How much funding is available?
$1,500,000 for a 24 month base period, plus a $500,000 option over 6 months, for $2,000,000 across 30 months if the option is exercised. Up to $25,000 in Technical and Business Assistance may be requested in addition to the cost ceiling.
When is the proposal deadline?
October 21, 2026. DARPA will not accept late proposals. Note the separate technical question deadline of October 14, 2026.
What must my existing prototype already do?
Six things. Autonomously find and localize casualties and report their location to within 2 meters. Assess trauma patterns and assign a trauma triage category. Perform accurate standoff vital-signs assessment including at minimum heart rate and respiratory rate. Operate at scale, meaning at least 20 casualties in a single scenario, assessment in under 90 seconds per casualty, and surveying a 30,000 square foot area without a battery change. Operate across diverse realistic environments, indoor and outdoor, daytime and nighttime, ideally but not required in rain and smoke. And produce a human-interpretable output through a graphical interface conveying casualty locations and priorities of care. The system must also be portable, with all components easily transported by a vehicle or drone.
How do I document that?
A written technical description or published report supported by data and videos demonstrating the prototype performing those capabilities in the stated environments, provided via link. Host the videos somewhere durable and accessible to Government reviewers from outside your network, and make sure the links stay live through the evaluation period, which can run 90 days past the close date.
Is this topic written for DARPA Triage Challenge participants?
Effectively yes. The topic states that the DARPA Triage Challenge has demonstrated that autonomous air and ground systems using standoff sensors can locate casualties, characterize injury patterns, and support triage prioritization in realistic mass casualty incident conditions, and that this solicitation uses DTC triage support capabilities as a starting point to extend into chemically hazardous environments. The DTC program summary is one of the six cited references.
Do I need to detect the chemical agent?
No, and this is a significant scoping decision. Agent detection is out of scope for this effort. The requirements table states that identification of the specific chemical agent is out of scope and that chemical-specific sensors are also out of scope. You are inferring a probable agent category from the casualty's physical presentation, the toxidrome, not measuring the chemical.
How many toxidromes must I address?
At least two chemical agent categories from Table 1. The minimum deliverable is a demonstrated prototype that detects at least two representative chemical toxidromes and applies appropriate initial treatments for the assessed toxidrome following human-in-the-loop treatment approval.
Which two toxidromes should I choose?
The choice has large engineering consequences. Cholinergic syndrome uses intramuscular delivery of atropine and pralidoxime. Opioid syndrome uses intranasal or intramuscular naloxone. Pulmonary syndrome uses bronchodilator delivery. Vesicant syndrome uses skin decontamination. But blood-agent, cyanide, syndrome requires IV or IO pharmaceutical delivery, and the table footnote specifies that this includes autonomous placement of an intravenous or intraosseous catheter, which is a substantially harder robotic task. Choosing routes that avoid autonomous vascular access is a materially easier path, and you should justify whichever pair you select.
What does airway management require?
Per the Table 1 footnote, airway management includes providing supplemental oxygen by mask AND escalating to either non-invasive, meaning bag-valve mask or mechanical, or invasive, meaning endotracheal intubation or surgical airway, ventilation. Airway management appears as an anticipated treatment for all five toxidrome categories.
How will toxidrome recognition be demonstrated?
Performers will demonstrate their platform's ability to recognize simulated toxidromes in silico, meaning computer-based simulation, and on high-fidelity mannikins with the simulated presentations outlined in Table 2. Those simulated cues include damp clothing and ground, constricted or dilated pupils, coughing sounds, specific respiratory rates, slow palpable pulses at wrist and groin, emesis positioned on the face and ground, sprayed liquid simulating damp skin, gelatin simulating blisters, scleral injection, wheezing on auscultation, cyanosis around the lips, and verbal non-responsiveness.
What sensing does that imply?
Read Table 2 as your sensing specification. It requires pupillometry, respiratory rate measurement, pulse assessment at the wrist and groin, auscultation of lung sounds, skin color and moisture assessment, blister detection, verbal responsiveness testing, and emesis detection. Several of these require close approach or contact rather than pure standoff sensing, which interacts with your mobility and manipulation design.
What is the intervention delivery requirement?
The platform must physically administer treatment appropriate to the chosen toxidrome according to Table 1 on a mannikin. The final demonstration requires the system payload and automation to administer treatment to at least 5 casualties in succession without battery changes or re-supply. Both are marked as required on a mannikin.
What platform should I propose?
DARPA is platform-agnostic: autonomous UAV and UGV are both acceptable, and the performer may choose the sensor suite excluding chemical-specific sensors. However, a single robust platform must operate across and transition between realistic environments, meaning difficult terrain, inside and outside of buildings, and potentially subterranean settings, and dedicated single-environment platforms are not sought.
Who makes the treatment decision?
A human, always. Treatment recommendations and options for each casualty shall be presented through a graphical interface to responders, and treatment decisions will always be made by humans. The topic states this three separate times. Whatever autonomy you propose for search, assessment, and navigation, the treatment decision is presented to a person.
What does DARPA say about failure modes?
Offerors are encouraged to propose the human-machine teaming arrangement that best improves decision quality and casualty outcomes, and to define how their system fails safely when conditions exceed its competence. That second element is a stated expectation, not a risk-section afterthought, and for an autonomous system administering medication it is central.
How is the end of program demonstration structured?
Detection and assessment may be validated computationally through assessment of a test set of images and videos showing injuries and clinical signs such as respiratory distress, pupillary changes, salivation, sweating, skin changes and blisters. Intervention delivery on multiple casualties must be validated by physical demonstration, required on a mannikin and over real terrain. The essential program output is a validated prototype.
How long can my technical volume be?
This topic uses the White Paper and Slide Deck format. The white paper shall not exceed 20 pages and the slide deck shall not exceed 15 slides. Refer to Appendix B, DARPA Direct to Phase II Instructions, for the content of each element and the commercialization strategy.
Can I ask questions through DSIP Topic Q&A?
No. DARPA states DSIP Topic Q&A will not be available for these topics. Technical questions go to SBIR_BAA@darpa.mil with the topic number in the subject line by October 14, 2026. Questions submitted within seven calendar days of the due date may not be answered. DARPA posts a consolidated FAQ, updated until one week before the due date.
Do I have to choose a contract type?
Yes. Proposers must state their requested contract type. DARPA may award FAR-based firm-fixed-price or cost-plus reimbursement contracts, or Other Transactions for Prototype under 10 U.S.C. 4021. Cost-plus requires your DCMA Final Determination Letter showing accounting system approval. An OT requires a completed Model OT plus OT Certifications in Volume 5. Firm-fixed-price requires no additional action.
Is the cost template mandatory?
Yes. Templates for Volume 2 and Volume 3 are on the DARPA Small Business website, and use of the DARPA Cost Proposal template is mandatory.
Are venture capital backed companies eligible?
Yes. Proposers more than 50 percent owned by multiple venture capital operating companies, hedge funds, private equity firms, or any combination as set forth in 13 CFR 121.702 are eligible, subject to registering with the SBA Company Registry Database before submitting, submitting the Majority-Owned VCOC, HF, and PEF Certification in Volume 5, and notifying the Contracting Officer if you enter that class after submitting but before award.
How will my proposal be evaluated?
Against the evaluation criteria in the DoW SBIR Program BAA. DARPA evaluates each conforming proposal in its entirety, documenting strengths and weaknesses relative to each criterion, then determines overall selectability. Proposals are not evaluated against each other. A selectable proposal is one where strengths outweigh weaknesses with no accumulated weaknesses requiring extensive negotiations or resubmission.
Will I get feedback if not selected?
Yes. DARPA will provide a technical evaluation narrative to the proposer for each proposal submitted in response to a topic, per the SBA SBIR/STTR Policy Directive. An informal feedback session may additionally be requested via sbir@darpa.mil, at DARPA's sole discretion.
What is the commercial market?
Autonomous systems capable of assessing and delivering life sustaining treatments during disaster responses, industrial chemical accidents, hazmat operations, and chemical terror attacks in which fire and EMS response will be delayed. Industrial chemical facilities, hazmat teams, fire departments in petrochemical corridors, and emergency management agencies all face the same hot-zone entry delay. Opioid and fentanyl mass exposure incidents map directly onto one of the five toxidrome categories and are a further civilian use case.
Who do I contact with questions?
The DARPA Small Business Programs Office at SBIR_BAA@darpa.mil for both program administration and topic technical questions, with the topic number in the subject line. DSIP technical support at DoDSBIRSupport@reisystems.com with a copy to SBIR_BAA@darpa.mil, Monday through Friday 9:00 a.m. to 5:00 p.m. ET. DARPA also offers free resources through DARPAConnect at DARPAConnect.us.
Positioning Advice for Companies Considering This Topic
Check the six feasibility capabilities before anything else. Phase I work is expected to have been completed before award, and the numbers are specific: 2 meter localization, sub-90-second assessment, 20 casualties, 30,000 square feet on one battery. These are measurements from a working system. If you cannot produce data and video for all six, the effort is better spent elsewhere.
Choose your two toxidromes on engineering grounds, then justify clinically. Autonomous IV or IO catheter placement, required for the cyanide category, is a different order of robotic difficulty from an intramuscular injection or intranasal spray. Cholinergic plus opioid gives you two clinically important categories with tractable delivery routes. If you choose the harder route, explain why your manipulation capability supports it.
Build the perception case from Table 2, not from generalities. DARPA told you exactly what cues the mannikins will present: pupil size, respiratory rate thresholds, palpable pulse rates, wheezing on auscultation, scleral injection, lip cyanosis, gelatin blisters, sprayed liquid, positioned emesis, verbal non-responsiveness. A proposal that walks those cues and states which sensor and algorithm addresses each is far more persuasive than one describing a general-purpose vision stack.
Solve the close-approach problem. Several Table 2 cues, notably auscultation and palpable pulse, are not standoff measurements. Your system has to get close enough to contact a casualty in a contaminated environment and do so safely, since safe physical interaction with high-fidelity mannikins is a stated requirement. That is a manipulation and safety problem distinct from search and navigation.
Take the human-in-the-loop interface seriously as a deliverable. It is mentioned three times, and it is the point where an autonomous system in a hot zone hands a life-or-death decision to a person who may be outside it. Show the interface: what the responder sees, how confidence is expressed, how they approve or decline, and what latency the loop introduces.
Define competence boundaries and fail-safe behavior explicitly. DARPA asked for it. An autonomous system that misreads a toxidrome and delivers the wrong drug is worse than one that declines and flags for human assessment. Saying where your system stops, and what it does when it stops, is a strength rather than an admission.
Design one platform for all environments. Difficult terrain, inside and outside buildings, potentially subterranean, with transitions between them, and dedicated single-environment platforms are explicitly not sought. If your strength is one domain, address the transition problem head on rather than hoping it goes unnoticed.
Budget the five-in-succession endurance requirement. Five treatments delivered without battery change or resupply, on top of a 30,000 square foot survey, is a real payload, power, and consumables engineering problem. Show the budget.
Read the DARPA Triage Challenge program summary and position against it. It is cited as the baseline this topic extends. Stating clearly what your system already does that DTC demonstrated, and what the chemical extension adds, frames your proposal in the agency's own terms.
Ground the medicine properly. Use DUMBBELS correctly, get the atropine and pralidoxime pairing right, understand why naloxone is intranasal or intramuscular, and know why vesicant treatment is decontamination rather than an antidote. The cited Marrs organophosphate chapter and Dembek volume are there for a reason, and clinical fluency separates a robotics company that understands the mission from one that has read a summary.
Use the slide deck for what slides do well. Fifteen slides alongside a 20 page white paper is a generous visual allowance. Platform photographs, sensing geometry diagrams, demonstration stills, and toxidrome cue mappings all communicate faster as images. Do not duplicate the white paper in bullet form.
