Risk-Aware Motion Planning in Partially Known Environments

被引:17
作者
Barbosa, Fernando S. [1 ]
Lacerda, Bruno [2 ]
Duckworth, Paul [2 ]
Tumova, Jana [1 ]
Hawes, Nick [2 ]
机构
[1] KTH Royal Inst Technol & Digital Futures, Stockholm, Sweden
[2] Univ Oxford, Oxford Robot Inst, Oxford, England
来源
2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC) | 2021年
基金
英国工程与自然科学研究理事会;
关键词
D O I
10.1109/CDC45484.2021.9683744
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recent trends envisage robots being deployed in areas deemed dangerous to humans, such as buildings with gas and radiation leaks. In such situations, the model of the underlying hazardous process might be unknown to the agent a priori, giving rise to the problem of planning for safe behaviour in partially known environments. We employ Gaussian process regression to create a probabilistic model of the hazardous process from local noisy samples. The result of this regression is then used by a risk metric, such as the Conditional Value-at-Risk, to reason about the safety at a certain state. The outcome is a risk function that can be employed in optimal motion planning problems. We demonstrate the use of the proposed function in two approaches. First is a sampling-based motion planning algorithm with an event-based trigger for online replanning. Second is an adaptation to the incremental Gaussian Process motion planner (iGPMP2), allowing it to quickly react and adapt to the environment. Both algorithms are evaluated in representative simulation scenarios, where they demonstrate the ability of avoiding high-risk areas.
引用
收藏
页码:5220 / 5226
页数:7
相关论文
共 29 条
[11]  
Gammell JD, 2015, IEEE INT CONF ROBOT, P3067, DOI 10.1109/ICRA.2015.7139620
[12]   Risk-Aware Motion Planning and Control Using CVaR-Constrained Optimization [J].
Hakobyan, Astghik ;
Kim, Gyeong Chan ;
Yang, Insoon .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2019, 4 (04) :3924-3931
[13]  
Jackson J., 2020, ARXIV200401821
[14]  
Kalakrishnan Mrinal, 2011, IEEE INT C ROBOTICS
[15]   Sampling-based algorithms for optimal motion planning [J].
Karaman, Sertac ;
Frazzoli, Emilio .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2011, 30 (07) :846-894
[16]  
Karlsson J., 2020, IFAC WORLD C
[17]  
Koller T, 2018, IEEE DECIS CONTR P, P6059, DOI 10.1109/CDC.2018.8619572
[18]  
Luders B. D., 2013, P AIAA GUID NAV CONT, P5097
[19]   How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics [J].
Majumdar, Anirudha ;
Pavone, Marco .
ROBOTICS RESEARCH, 2020, 10 :75-84
[20]  
Marchant R, 2014, UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, P553