Computing worst-case robust strategies in pursuit-evasion games (PEGs) is time-consuming, especially when real-world factors like partial observability are considered. While important for general security purposes, real-time applicable pursuit strategies for graph-based PEGs are currently missing when the pursuers only have imperfect information about the evader's position. Although state-of-the-art reinforcement learning (RL) methods like Equilibrium Policy Generalization (EPG) and Grasper provide guidelines for learning graph neural network (GNN) policies robust to different game dynamics, they are restricted to the scenario of perfect information and do not take into account the possible case where the evader can predict the pursuers' actions. This paper introduces the first approach to worst-case robust real-time pursuit strategies (R2PS) under partial observability. We first prove that a traditional dynamic programming (DP) algorithm for solving Markov PEGs maintains optimality under the asynchronous moves by the evader. Then, we propose a belief preservation mechanism about the evader's possible positions, extending the DP pursuit strategies to a partially observable setting. Finally, we embed the belief preservation into the state-of-the-art EPG framework to finish our R2PS learning scheme, which leads to a real-time pursuer policy through cross-graph reinforcement learning against the asynchronous-move DP evasion strategies. After reinforcement learning, our policy achieves robust zero-shot generalization to unseen real-world graph structures and consistently outperforms the policy directly trained on the test graphs by the existing game RL approach.

This paper studies the problem of multi-robot pursuit of how to coordinate a group of defending robots to capture a faster attacker before it enters a protected area. Such operation for defending robots is challenging due to the unknown avoidance strategy and higher speed of the attacker, coupled with the limited communication capabilities of defenders. To solve this problem, we propose a parameterized formation controller that allows defending robots to adapt their formation shape using five adjustable parameters. Moreover, we develop an imitation-learning based approach integrated with model predictive control to optimize these shape parameters. We make full use of these two techniques to enhance the capture capabilities of defending robots through ongoing training. Both simulation and experiment are provided to verify the effectiveness and robustness of our proposed controller. Simulation results show that defending robots can rapidly learn an effective strategy for capturing the attacker, and moreover the learned strategy remains effective across varying numbers of defenders. Experiment results on real robot platforms further validated these findings.

This article investigates the practical scenarios of chasing an adversarial evader in an unbounded environment with cluttered obstacles. We propose a Voronoi-based decentralized algorithm for multiple pursuers to encircle and capture the evader by reacting to collisions. An efficient approach is presented for constructing an obstacle-aware evader-centered bounded Voronoi cell (OA-ECBVC), which strictly ensures collision avoidance in various obstacle scenarios when pursuing the evader. The evader can be efficiently enclosed in a convex hull given random initial configurations. Furthermore, to cooperatively capture the evader, each pursuer continually compresses the boundary of its OA-ECBVC to quickly reduce the movement space of the evader while maintaining encirclement. Our OA-ECBVC algorithm is validated in various simulated environments with different dynamic systems of robots. Real-time performance of resisting uncertainties shows the superior reliability of our method for deployment on multiple robot platforms.

Development of guidance, navigation and control frameworks/algorithms for swarms attracted significant attention in recent years. That being said, algorithms for planning swarm allocations/trajectories for engaging with enemy swarms is largely an understudied problem. Although small-scale scenarios can be addressed with tools from differential game theory, existing approaches fail to scale for large-scale multi-agent pursuit evasion (PE) scenarios. In this work, we propose a reinforcement learning (RL) based framework to decompose to large-scale swarm engagement problems into a number of independent multi-agent pursuit-evasion games. We simulate a variety of multi-agent PE scenarios, where finite time capture is guaranteed under certain conditions. The calculated PE statistics are provided as a reward signal to the high level allocation layer, which uses an RL algorithm to allocate controlled swarm units to eliminate enemy swarm units with maximum efficiency. We verify our approach in large-scale swarm-to-swarm engagement simulations.

The main contribution of this paper is a novel sensory feedback control law for an octopus arm. The control law is inspired by, and helps integrate, several observations made by biologists. The proposed control law is distinct from prior work which has mainly focused on open-loop control strategies. Several analytical results are described including characterization of the equilibrium and its stability analysis. Numerical simulations demonstrate life-like motion of the soft octopus arm, qualitatively matching behavioral experiments. Quantitative comparison with bend propagation experiments helps provide the first explanation of such canonical motion using a sensory feedback control law. Several remarks are included that help draw parallels with natural pursuit strategies such as motion camouflage or classical pursuit.

We present an alternative form AI that avoids limited type of interaction, namely the AI agents acting independently of each other rather than working together as a team. To do so, we add the multi-agent functionality to the AI for a simple pursuit game. Initially the AI directs each agent independently to pursue the target player. These agents then suffer from collision and overlapping such that the player can evade the clustered agents without difficulty. Next we introduce our multi-agent AI that coordinates the efforts of the enemy agents so that they stay in formation and work together to corner the player. In so doing we wish to show that this greatly improves the quality of gameplay and the realism simulated by the AI. Further, this upholds the original intention of the AI as designed by the developers and avoids unrealistic “cheats” to circumvent the intended gameplay. While this research is centered in gaming, we also believe that it has further reaching applications in security, simulations, and robotics.