|
While infantry can seamlessly traverse many different environments, current autonomous robots cannot. The gap that exists between human and robotic mobility is evident in the degree of hands-on teleoperation that is required to use today’s UGVs, such as the PackBot and the Talon. The next advance for ground-based robots will be the development of perception, planning, and control systems that will enable UGVs to autonomously navigate in the same environments, and at the
same speeds, as dismounted infantry. This autonomous capability is a necessary prerequisite for the realization of the potential of UGVs as tactical multipliers. We envision a new research program on autonomous modeling and navigation, with the goal of enabling small (e.g., man-packable) UGVs to move alongside their human counterparts through virtually any environment, whether indoor or outdoor. In support of this new program, we propose an exploratory project to study the key challenges in closing the loop on autonomous perception and action in challenging terrain. The primary objective of the proposed project is to demonstrate the first robot to autonomously traverse challenging 3-D terrain with onboard sensing and online processing. The robot’s perception, planning, and execution capabilities will operate in unmodified environments, both indoor and outdoor. This is a joint project with Stanford University and Boston Dynamics.
| |
