Mobility and Manipulation Thrust (MoMAT)
Lead: Chris Atkeson, Carnegie Mellon
A unifying theme for MoMAT is the provision of safe mobility and manipulation for users, caregivers, their environments, and modes of failure of assistive devices. This is a big challenge for QoLT.
MoMAT research is focused on:
- Planning Algorithms: New approaches to planning and control are a key component to improving autonomy of assistive devices. Algorithms must be real-world-ready so they reliably work in natural environments. They also need to function properly based on real-time sensor data input rather than models of a simulated world.
- Personal Safety Systems: We have an opportunity to monitor for risky behavior that leads to accidents and falls in home manipulation as well as unassisted and assisted locomotion, and act to change behavior to reduce risk. MoMAT projects bring together expertise in human behavior as well as a robotics perspective to analyze accidents. We are developing simulation and robotic models of how accidents occur, and what can be done to reduce their occurrence and their effect.
- Soft Manipulation: Soft physical interaction with humans is a relatively undeveloped area. No current humanoid robots are back-drivable, for example, and those that implement soft physical interaction do so only at selected sites using contact force sensing. Soft manipulation of fragile humans is a new challenging area for robotics, and we intend to pioneer this area.