Goal-Aware RSS for Complex Scenarios via Program Logic

被引:5
|
作者
Hasuo, Ichiro [1 ,2 ]
Eberhart, Clovis [1 ,3 ]
Haydon, James [1 ]
Dubut, Jeremy [1 ,3 ]
Bohrer, Rose [4 ]
Kobayashi, Tsutomu [1 ]
Pruekprasert, Sasinee [1 ]
Zhang, Xiao-Yi [1 ]
Pallas, Erik Andre
Yamada, Akihisa [1 ]
Suenaga, Kohei [1 ,5 ]
Ishikawa, Fuyuki [1 ,6 ]
Kamijo, Kenji [6 ]
Shinya, Yoshiyuki [6 ]
Suetomi, Takamasa [6 ]
机构
[1] Natl Inst Informat, Tokyo 1018430, Japan
[2] SOKENDAI Grad Univ Adv Studies, Hayama 1018430, Japan
[3] Japanese French Lab Informat IRL 3527, Tokyo 1350064, Japan
[4] Worcester Polytech Inst, Dept Comp Sci, Worcester, MA 01609 USA
[5] Kyoto Univ, Grad Sch Informat, Kyoto 6068501, Japan
[6] Mazda Motor Corp, Fuchu 7308670, Japan
来源
关键词
Safety; Automobiles; Collision avoidance; Intelligent vehicles; Cognition; Planning; Computer architecture; Automated driving; differential dynamics; Floyd-Hoare logic; program logic; responsibility-sensitive safety (RSS); rule-based safety; safety; simplex architecture;
D O I
10.1109/TIV.2022.3169762
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce a goal-aware extension of responsibility sensitive safety (RSS), a recent methodology for rule-based safety guarantee for automated driving systems (ADS). Making RSS rules guarantee goal achievement-in addition to collision avoidance as in the original RSS-requires complex planning over long sequences of manoeuvres. To deal with the complexity, we introduce a compositional reasoning framework based on program logic, in which one can systematically develop RSS rules for smaller subscenarios and combine them to obtain RSS rules for bigger scenarios. As the basis of the framework, we introduce a program logic dFHL that accommodates continuous dynamics and safety conditions. Our framework presents a dFHL-based workflow for deriving goal-aware RSS rules; we discuss its software support, too. We conducted experimental evaluation using RSS rules in a safety architecture. Its results show that goal-aware RSS is indeed effective in realising both collision avoidance and goal achievement.
引用
收藏
页码:3040 / 3072
页数:33
相关论文
共 50 条
  • [1] Goal-Aware Neural SAT Solver
    Ozolins, Emils
    Freivalds, Karlis
    Draguns, Andis
    Gaile, Eliza
    Zakovskis, Ronalds
    Kozlovics, Sergejs
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [2] The Goal Behind the Action: Toward Goal-Aware Systems and Applications
    Papadimitriou, Dimitra
    Koutrika, Georgia
    Mylopoulos, John
    Velegrakis, Yannis
    ACM TRANSACTIONS ON DATABASE SYSTEMS, 2016, 41 (04):
  • [3] Goal-aware Team Affiliation in Collectives of Autonomous Robots
    Esterle, Lukas
    2018 12TH IEEE INTERNATIONAL CONFERENCE ON SELF-ADAPTIVE AND SELF-ORGANIZING SYSTEMS (SASO 2018), 2018, : 90 - 99
  • [4] Leveraging Large Language Models for Goal-aware Interactive Recommendations
    Said, Alan
    Willemsen, Martijn
    Marinho, Leandro Balby
    Silva, Itallo
    PROCEEDINGS OF THE 11TH CONFERENCE ON HUMAN-AGENT INTERACTION, HAI 2023, 2023, : 464 - 466
  • [5] Goal-Aware Robocentric Mapping and Navigation of a Quadrotor Unmanned Aerial Vehicle
    Biswas, Srijanee
    Sharma, Rajnikant
    JOURNAL OF AEROSPACE INFORMATION SYSTEMS, 2021, 18 (08): : 488 - 505
  • [6] Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning
    Kim, Kibeom
    Lee, Min Whoo
    Kim, Yoonsung
    Ryu, Je-Hwan
    Lee, Minsu
    Zhang, Byoung-Tak
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [7] Augmenting sensorimotor control using “goal-aware” vibrotactile stimulation during reaching and manipulation behaviors
    Emmanouil Tzorakoleftherakis
    Todd D. Murphey
    Robert A. Scheidt
    Experimental Brain Research, 2016, 234 : 2403 - 2414
  • [8] Goal-aware generative adversarial imitation learning from imperfect demonstration for robotic cloth manipulation
    Tsurumine, Yoshihisa
    Matsubara, Takamitsu
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2022, 158
  • [9] Augmenting sensorimotor control using "goal-aware" vibrotactile stimulation during reaching and manipulation behaviors
    Tzorakoleftherakis, Emmanouil
    Murphey, Todd D.
    Scheidt, Robert A.
    EXPERIMENTAL BRAIN RESEARCH, 2016, 234 (08) : 2403 - 2414
  • [10] BOARD-AI: A goal-aware modeling interface for systems engineering, combining machine learning and plan recognition
    Castellanos-Paez, Sandra
    Hili, Nicolas
    Albore, Alexandre
    Perez-Sanagustin, Mar
    FRONTIERS IN PHYSICS, 2022, 10