National Robotics Initiative (NRI): Toward Humanoid Avatar Robots for Co-Exploration of Hazardous Environments

Extend existing open source robotics software libraries to make them more transparent, directable, and predictable in the avatar system. Improve balance and walking algorithms. Improve humanoid motion planning in complex, dynamic, and unstructured environments, such as the scene of a disaster or surface of another planet. Demonstrate alternate approach to pure tele-operation or pure autonomy. Demonstrate feasibility of using human-humanoid avatar robot teams for co-exploration of hazardous environments using Robonaut 2 as a test-bed. 

The proposed research will address several unsolved problems in humanoid robot balance and walking algorithms, humanoid motion planning in complex dynamic and unstructured environments, and telepresence interfaces. It will demonstrate an alternate approach to pure teleoperation or pure autonomy. It will demonstrate the feasibility of using human-humanoid avatar robot teams for coexploration of hazardous environments. The fully matured technology under this research task would provide:

• Coactive interfaces, which explicitly take into account the interdependence of cooperative tasks - Today's robots are typically fully teleoperated, placing a large burden on the operator, or have full autonomy that is opaque, leading to automation surprises.    
• Bipedal walking and balance algorithms - Today's best humanoids still fall over from slight pushes, and cannot walk on slightly rough ground without a high-precision model of the ground.
• Humanoid locomotion planning - There are many impressive planning tools available that we will leverage, but work still needs to be done on applying these tools to complex, unstructured, and dynamic hazardous environments, as well as integrating manipulation and dynamic locomotion.
• Multi-sensory telepresence interfaces - Appropriate use of telepresence interfaces that project not only visual, but also tactile and audio information to the operator, may lead to improved situational awareness.

Search & Rescue / Disaster Recovery Robots – In the near future, this technology could be used to enable humanoid avatar robots to assist in exploration and recovery of disaster sites. While a variety of robots will be used, humanoid robots will fill a special role, since they can potentially get to the same places, perform the same tasks, and use the same tools as humans.

Space Exploration Robots - Remotely operated humanoid avatar robots could one day work cooperatively with humans to explore planetary surfaces and build space colonies.

Inspiration - Human and humanoid avatar co-exploration of hazardous areas and planetary surfaces has the potential to capture the minds and imaginations of current and future scientists and engineers, and the public at large, leading to enhanced educational motivation and national pride.

Open Source Software - This project will involve a variety of post-docs, graduate, undergraduate, and high school students. All developed software will be made open source and freely available. Research will be disseminated and communicated through various means, including incorporation into a University of West Florida class on bipedal walking robots, and existing IHMC informal science education programs.

This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.