Loading activity…
@songshuran
Assistant Professor @Stanford University working on #Robotics #AI #ComputerVision
AI
A post argues that a “Chronos Policy” should model physical time from observation through inference to action execution.
AI
A user says NEEDLEWORK stitches suboptimal and failed robot trajectories to improve demonstration quality and diversity.
AI
A post sharing the approach says it avoids confining robot hands to a low-dimensional “eigengrasp” space.
AI
Stanford professor shares suggestion on social media referencing prior post by @haqhuy
AI
Video shows dual-arm robot learning new manipulations from seconds of human demonstration after pretraining.
