2025-03-07 マサチューセッツ工科大学(MIT)
＜関連情報＞
- https://news.mit.edu/2025/robotic-helper-mistakes-nudging-in-right-direction-0307
- https://arxiv.org/abs/2411.16627
人間とのインタラクションによる推論時間型ポリシー・ステアリング Inference-Time Policy Steering through Human Interactions
Yanwei Wang, Lirui Wang, Yilun Du, Balakumar Sundaralingam, Xuning Yang, Yu-Wei Chao, Claudia Perez-D’Arpino, Dieter Fox, Julie Shah
arXive Submitted on 25 Nov 2024
DOI:https://doi.org/10.48550/arXiv.2411.16627
Abstract
Generative policies trained with human demonstrations can autonomously accomplish multimodal, long-horizon tasks. However, during inference, humans are often removed from the policy execution loop, limiting the ability to guide a pre-trained policy towards a specific sub-goal or trajectory shape among multiple predictions. Naive human intervention may inadvertently exacerbate distribution shift, leading to constraint violations or execution failures. To better align policy output with human intent without inducing out-of-distribution errors, we propose an Inference-Time Policy Steering (ITPS) framework that leverages human interactions to bias the generative sampling process, rather than fine-tuning the policy on interaction data. We evaluate ITPS across three simulated and real-world benchmarks, testing three forms of human interaction and associated alignment distance metrics. Among six sampling strategies, our proposed stochastic sampling with diffusion policy achieves the best trade-off between alignment and distribution shift. Videos are available at this https URL.
