BlenDAgger: Blended Shared Control for Interactive Imitation Learning
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions.
초록에서 가져왔습니다. 요약을 준비 중입니다.