Search this site
Embedded Files
Skip to main content
Skip to navigation
Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real
Home
D'Kitty Coordinate Videos
D'Kitty Push Videos
D'Kitty Avoid Videos
Low-level Videos
Failure Modes
Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real
Home
D'Kitty Coordinate Videos
D'Kitty Push Videos
D'Kitty Avoid Videos
Low-level Videos
Failure Modes
More
Home
D'Kitty Coordinate Videos
D'Kitty Push Videos
D'Kitty Avoid Videos
Low-level Videos
Failure Modes
D'Kitty Avoid
A hierarchical policy is trained in sim to move to a target while avoiding an obstacle (red box).
Learned behavior transfers to the real world (target given by position of HTC Vive controller on the ground).
Behaviors generalize to settings in which the target or box is moving.
Google Sites
Report abuse
Page details
Page updated
Google Sites
Report abuse