Contingency Games for Multi-Agent Interaction

被引:0
|
作者
Peters, Lasse [1 ]
Bajcsy, Andrea [2 ]
Chiu, Chih-Yuan [3 ]
Fridovich-Keil, David [4 ]
Laine, Forrest [5 ]
Ferranti, Laura [1 ]
Alonso-Mora, Javier [1 ]
机构
[1] Delft Univ Technol, Dept Cognit Robot, NL-2628 CD Delft, Netherlands
[2] Carnegie Mellon Univ, Robot Inst, Pitts, GA 15213 USA
[3] Univ Calif Berkeley, Dept EECS, Berkeley, CA 94720 USA
[4] UT Austin, Dept Aerosp Engn & Engn Mech, Austin, TX 78712 USA
[5] Vanderbilt Univ, Dept Comp Sci, Nashville, TN 37212 USA
关键词
Games; Uncertainty; Contingency management; Robots; Planning; Trajectory; Pedestrians; Planning under uncertainty; human-aware motion planning; motion and path planning; DYNAMIC-GAMES;
D O I
10.1109/LRA.2024.3354548
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Contingency planning, wherein an agent generates a set of possible plans conditioned on the outcome of an uncertain event, is an increasingly popular way for robots to act under uncertainty. In this work we take a game-theoretic perspective on contingency planning, tailored to multi-agent scenarios in which a robot's actions impact the decisions of other agents and vice versa. The resulting contingency game allows the robot to efficiently interact with other agents by generating strategic motion plans conditioned on multiple possible intents for other actors in the scene. Contingency games are parameterized via a scalar variable which represents a future time when intent uncertainty will be resolved. By estimating this parameter online, we construct a game-theoretic motion planner that adapts to changing beliefs while anticipating future certainty. We show that existing variants of game-theoretic planning under uncertainty are readily obtained as special cases of contingency games. Through a series of simulated autonomous driving scenarios, we demonstrate that contingency games close the gap between certainty-equivalent games that commit to a single hypothesis and non-contingent multi-hypothesis games that do not account for future uncertainty reduction.
引用
收藏
页码:2208 / 2215
页数:8
相关论文
共 50 条
  • [1] Contingency Detection in Multi-Agent Interactions
    Staley, James
    Short, Elaine Schaertl
    [J]. HRI '21: COMPANION OF THE 2021 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, 2021, : 225 - 228
  • [2] Multi-agent modeling of interaction-based card games
    Hurwitz, Evan
    Marwala, Tshilidzi
    [J]. GAMEON-NA 2006: 3RD INTERNATIONAL NORTH-AMERICAN CONFERENCE ON INTELLIGENT GAMES AND SIMULATION, 2007, : 23 - 28
  • [3] Multi-agent based pedagogical games
    Giraffa, LMM
    Viccari, RM
    Self, J
    [J]. INTELLIGENT TUTORING SYSTEMS, 1998, 1452 : 607 - 607
  • [4] Multi-Agent Flag Coordination Games
    Marzagao, David Kohan
    Rivera, Nicolas
    Cooper, Colin
    McBurney, Peter
    Steinhofel, Kathleen
    [J]. AAMAS'17: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2017, : 1442 - 1450
  • [5] Multi-Agent Petri-Games
    Tagiew, Rustam
    [J]. 2008 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR MODELLING CONTROL & AUTOMATION, VOLS 1 AND 2, 2008, : 130 - 135
  • [6] Multi-agent Differential Graphical Games
    Vamvoudakis, Kyriakos G.
    Lewis, F. L.
    [J]. 2011 30TH CHINESE CONTROL CONFERENCE (CCC), 2011, : 4932 - 4939
  • [7] Mainstream games in the multi-agent classroom
    de Melo, Celso
    Prada, Rui
    Raimundo, Guilherme
    Pardal, Joana Paulo
    Pinto, Helena Sofia
    Paiva, Ana
    [J]. 2006 IEEE/WIC/ACM INTERNATIONAL CONFERENCE ON INTELLIGENT AGENT TECHNOLOGY, PROCEEDINGS, 2006, : 757 - +
  • [8] A Generic Agent Architecture for Cooperative Multi-agent Games
    Marinheiro, Joao
    Cardoso, Henrique Lopes
    [J]. ICAART: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL 1, 2017, : 107 - 118
  • [9] A Contingency Response Multi-agent System for Oil Spills
    Mata, Aitor
    Tapia, Dante I.
    Gonzalez, Angelica
    Perez, Belen
    [J]. 7TH INTERNATIONAL CONFERENCE ON PRACTICAL APPLICATIONS OF AGENTS AND MULTI-AGENT SYSTEMS (PAAMS 2009), 2009, 55 : 274 - +
  • [10] Intelligent multi-agent support for the contingency management system
    Sheremetov, LB
    Contreras, M
    Valencia, C
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2004, 26 (01) : 57 - 71