Goal Control for UGV Path Planning in Complex Environment

With the development of science and technology, the environment where the Unmanned Ground Vehicles (UGVs) patrol is complex for the cooperative and adversarial interactions. The actions performed by the UGVs can be observed by others which might be cooperators or adversaries. In order to fulfill the battle field patrol task, the goals of path planning for UGVs should be controlled in the mixed cooperative and adversarial environment. In this paper, we first define the goal control problem among three different roles (actor, cooperative observer, and adversarial observer), where the actor (UGV) need to reveal the real goal tied with the truthful path to the cooperative observer while hide the real goal tied with the deceptive path to the adversarial observer. Therefore, we propose one method of generating truthful or deceptive path depending on the judgement of the current observer type. Finally, indoor robot demonstration has been performed to verify the applicable of our proposed method.

[1]  Miquel Ramírez,et al.  Action Selection for Transparent Planning , 2018, AAMAS.

[2]  Yi Wu,et al.  Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments , 2017, NIPS.

[3]  Sebastian Sardiña,et al.  Cost-Based Goal Recognition in Navigational Domains , 2019, J. Artif. Intell. Res..

[4]  Daniel Borrajo,et al.  Counterplanning using Goal Recognition and Landmarks , 2018, IJCAI.

[5]  Michal Štolba Reveal or Hide: Information Sharing in Multi-Agent Planning , 2017 .

[6]  Sebastian Sardiña,et al.  Deceptive Path-Planning , 2017, IJCAI.

[7]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[8]  Subbarao Kambhampati,et al.  Balancing Goal Obfuscation and Goal Legibility in Settings with Cooperative and Adversarial Observers , 2019, ArXiv.

[9]  Yu Zhang,et al.  Plan explicability and predictability for robot task planning , 2015, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[11]  Erez Karpas,et al.  Goal Recognition Design for Non-Optimal Agents , 2015, AAAI.

[12]  Joshua B. Tenenbaum,et al.  Learning to Share and Hide Intentions using Information Regularization , 2018, NeurIPS.

[13]  Wei Gao,et al.  Goal Recognition Control under Network Interdiction Using a Privacy Information Metric , 2019, Symmetry.

[14]  Ronen I. Brafman,et al.  Representing and Planning with Interacting Actions and Privacy , 2018, ICAPS.

[15]  Erez Karpas,et al.  Goal Recognition Design , 2014, ICAPS.

[16]  Shlomo Zilberstein,et al.  Integration of Planning with Recognition for Responsive Interaction Using Classical Planners , 2017, AAAI.

[17]  Subbarao Kambhampati,et al.  A Unified Framework for Planning in Adversarial and Cooperative Environments , 2018, AAAI.