About this CFP
Amazon is advancing robotics technology to enable capable, safe, and intelligent robots that can operate alongside people in complex real-world environments. Amazon Robotics designs, codes, builds, and manufactures game-changing software applications, control systems, robotics, and related hardware that is revolutionizing Amazon's operations across the globe. We welcome proposals in the following research topics:
- AI for Robotics and Human-Robot Interaction: Topics of interest include multi-modal perception of complex 3D scenes and situations; multi-modal task grounding from human instructions spanning language, vision, gestures, and references to priors; and understanding long-term object dynamics in environments shared with people.
- Areas of interest also include the effects of robot embodiment, and personality expression on user engagement, trust formation, and long-term acceptance in repeated interactions; legibility and transparency of autonomous robot intent, action, and decision-making in collaborative settings; and multi-modal communication strategies for robot error recovery, clarification, and repair in collaborative tasks.
- Autonomous Navigation: Relevant areas include geometry-aware navigation accounting for the robot's configuration and payload; integration of multi-modal perception for navigation; reinforcement learning-based control policies for task-specific object interaction (e.g., doors and drawers); and scalable data generation for policy training.
- Manipulation
- Manipulation in Cluttered and Unstructured Environments: Topics of interest include manipulation under occlusion, stacking, and packing scenarios; compositional approaches to general-purpose manipulation; and non-prehensile manipulation related to contact force sensing and control; compliant control; generalizable surface and sweeping manipulation, impulsive manipulation, use of large multimodal models, and teleoperation.
- Physical Reasoning and World Models: Relevant topics include world models learned from multimodal sensory data (vision, force, and tactile); causal reasoning about contact dynamics; semantic abstractions for contact-rich tasks; and simulation and synthetic data for real-world transfer.
- Data for Manipulation: Topics of interest include physically grounded scenario and trajectory synthesis, including long-horizon task sequences; cross-embodiment transfer and retargeting; demonstration transfer across manipulation targets; synthetic data augmentation for novel object manipulation; and automated data quality evaluation methods.
- Safety-Critical Control and Safe Reinforcement Learning: Relevant areas include safety for manipulation in complex environments; compliant body control and safe contact-rich control; body control robust to external disturbances; verification and monitoring of RL controller performance; safety-constrained reinforcement learning; and robust and verifiable human detection and localization.
Theoretical advances, creative new ideas, and practical applications are all welcome
Timeline
- Submission period: March 25 — May 6, 2026 (11:59 PM Pacific Time).
- Decision letters will be sent out in August 2026
Award details
Selected Principal Investigators (PIs) may receive the following:
- Unrestricted funds, no more than $50,000 USD on average
- AWS Promotional Credits, no more than $50,000 USD on average
- Training resources, including AWS tutorials and hands-on sessions with Amazon scientists and engineers
Awards are structured as one-time unrestricted gifts. The budget should include a list of expected costs specified in USD, and should not include administrative overhead costs. The final award amount will be determined by the awards panel.
Eligibility requirements
Please refer to the ARA Program rules on the rules and eligibility page.
Proposal requirements
Proposals should be prepared according to the proposal template and are encouraged to be a maximum of 3 pages, not including Appendices.
Selection criteria
Robotics will make the funding decisions based on the potential impact to the research community and the quality of the scientific content.
Expectations from recipients
To the , award recipients may acknowledge support from ARA (e.g., (“Research reported in this [publication/press release] was supported by an Amazon Research Award, [Cycle /Year].“). Award recipients will inform ARA of publications, presentations, code and data releases, blogs/social media posts, and other speaking engagements referencing the results of the supported research or the Award. Award recipients are expected to provide updates and feedback to ARA via surveys or reports on the status of their research. Award recipients will have an opportunity to work with ARA on an informational statement about the awarded project that may be used to generate visibility for their institutions and ARA.