arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.05519cs.ROcs.AI

机器人在协作与竞争中影响人类以揭示其目标

Robots Influencing Humans to Reveal their Goals during Collaboration and Competition

  • Yale University(耶鲁大学)
  • Massachusetts Institute of Technology(麻省理工学院)
  • University of Colorado, Boulder(科罗拉多大学博尔德分校)

机构由 AI 辅助整理,请以论文原文为准。

Debasmita Ghose, Oz Gitelson, Michal Lewkowicz, Jake Brawer, Marynel Vazquez, Brian Scassellati

AI总结:

提出一种统一策略,通过引导人类走向关键决策点,利用滚动时域规划器平衡任务与信息,在协作和竞争场景中实现更早更准的目标推断。

AI中文摘要:

我们提出了一种在人机交互中快速推断目标的统一策略。核心思想是驱动人类走向关键决策点(CDPs)——在这些状态下,竞争性的人类策略会规定不同的后续动作,从而最大程度地揭示目标。我们使用目标条件策略散度度量来形式化CDPs,并将其纳入一个滚动时域规划器中,该规划器在优化平衡任务进展和信息获取的成本函数的同时,探索未来的动作序列。我们在一个协作的、完全可观察的烹饪任务和一个竞争的、部分可观察的捉迷藏游戏中评估了这种方法,每个任务都在仿真和真实机器人上进行。在两种场景中,我们的方法都比基线策略更准确、更早地推断出人类目标。

英文摘要:

We propose a unified strategy for fast goal inference in human-robot interaction. The core idea is to drive the human toward Critical Decision Points (CDPs)-states where competing human strategies prescribe different next actions and thus maximally reveal the goal. We formalise CDPs using a goal-conditioned policy divergence measure and incorporate them into a Receding-Horizon Planner that explores future action sequences while optimizing a cost function balancing task progress and information gain. We evaluate this approach in both a collaborative, fully observable cooking task and a competitive, partially observable hide-and-seek game, each in simulation and on real robots. In both scenarios, our method infers human goals more accurately and earlier than baseline strategies.

补充信息

↑