期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 6, 期 1, 页码 24-31出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2020.3028049
关键词
Robots; Predictive models; Robust control; Computational modeling; Decision making; Data models; Collision avoidance; Safety in HRI; human-aware motion planning
类别
资金
- NSF CAREER award
- DARPA Assured Autonomy
- NSF CPS VeHICal
Designing human motion predictors for robots operating in close physical proximity to people is a challenge, as it requires balancing safety and efficiency. One approach is to use robust control predictors, which can be too conservative, while another is through intent-driven predictors, which can lead to unsafe maneuvers if intent models are misspecified. A novel predictor combining robust control and intent-driven human modeling is proposed to provide robustness against misspecified models while reducing conservatism, demonstrated through simulation and hardware tests.
Designing human motion predictors which preserve safety while maintaining robot efficiency is an increasingly important challenge for robots operating in close physical proximity to people. One approach is to use robust control predictors that safeguard against every possible future human state, leading to safe but often too conservative robot plans. Alternatively, intent-driven predictors explicitly model how humans make decisions given their intent, leading to efficient robot plans. However, when the intent model is misspecified, the robot might confidently plan unsafe maneuvers. In this letter, we combine ideas from robust control and intent-driven human modelling to formulate a novel human motion predictor which provides robustness against misspecified human models, but reduces the conservatism of traditional worst-case predictors. Our approach predicts the human states by trusting the intent-driven model to decide only which human actions are completely unlikely. We then safeguard against all likely enough actions, much like a robust control predictor. We demonstrate in simulation and hardware how our approach safeguards against misspecified human intent models while not leading to overly conservative robot plans.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据