5 papers · 1 filter
Should Collaborative Robots be Transparent?
Shahabedin Sagheb, Soham Gandhi, Dylan P. Losey
We often assume that robots which collaborate with humans should behave in ways that are transparent (e.g., legible, explainable). These transparent robots intentionally choose act…
LIMIT: Learning Interfaces to Maximize Information Transfer
Benjamin A. Christie, Dylan P. Losey
Robots can use auditory, visual, or haptic interfaces to convey information to human users. The way these interfaces select signals is typically pre-defined by the designer: for in…
Stable-BC: Controlling Covariate Shift with Stable Behavior Cloning
Shaunak A. Mehta, Yusuf Umut Ciftci, Balamurugan Ramachandran +2
Behavior cloning is a common imitation learning paradigm. Under behavior cloning the robot collects expert demonstrations, and then trains a policy to match the actions taken by th…
Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks
Shaunak A. Mehta, Soheil Habibian, Dylan P. Losey
Robot arms should be able to learn new tasks. One framework here is reinforcement learning, where the robot is given a reward function that encodes the task, and the robot autonomo…
SARI: Shared Autonomy across Repeated Interaction
Ananth Jonnavittula, Shaunak A. Mehta, Dylan P. Losey
Assistive robot arms try to help their users perform everyday tasks. One way robots can provide this assistance is shared autonomy. Within shared autonomy, both the human and robot…