Article

CHOP: Counterfactual human preference labels improve obstacle avoidance in visuomotor navigation policies

The authors propose CHOP, which fine-tunes visuomotor navigation policies with counterfactual human preference labels to align them with human intuition about safety and obstacle avoidance. On the SCAND dataset, multiple advanced models fine-tuned with CHOP reduced near-collision events by an average of 49.7%, decreased deviation from human-preferred trajectories by 45.0%, and increased average obstacle clearance by 19.8%.

Part of the event: CHOP: Counterfactual Human Preference Labels Improve Navigation Obstacle Avoidance

This page provides a summary and source link only.