Scaling Team Coordination on Graphs with Reinforcement Learning

This paper studies Reinforcement Learning (RL) techniques to enable team coordination behaviors in graph environments with support actions among teammates to reduce the costs of traversing certain risky edges in a centralized manner. While classical approaches can solve this non-standard multi-agent path planning problem by converting the original Environment Graph (EG) into a Joint State Graph (JSG) to implicitly incorporate the support actions, those methods do not scale well to large graphs and teams. To address this curse of dimensionality, we propose to use RL to enable agents to learn such graph traversal and teammate supporting behaviors in a data-driven manner. Specifically, through a new formulation of the team coordination on graphs with risky edges problem into Markov Decision Processes (MDPs) with a novel state and action space, we investigate how RL can solve it in two paradigms: First, we use RL for a team of agents to learn how to coordinate and reach the goal with minimal cost on a single EG. We show that RL efficiently solves problems with up to 20/4 or 25/3 nodes/agents, using a fraction of the time needed for JSG to solve such complex problems; Second, we learn a general RL policy for any $N$-node EGs to produce efficient supporting behaviors. We present extensive experiments and compare our RL approaches against their classical counterparts.

Manta Ray Inspired Flapping-Wing Blimp

Lighter-than-air vehicles or blimps, are an evolving platform in robotics with several beneficial properties such as energy efficiency, collision resistance, and ability to work in close proximity to human users. While existing blimp designs have mainly used propeller-based propulsion, we focus our attention to an alternate locomotion method, flapping wings. Specifically, this paper introduces a flapping-wing blimp inspired by manta rays, in contrast to existing research on flapping-wing vehicles that draw inspiration from insects or birds. We present the overall design and control scheme of the blimp as well as the analysis on how the wing performs. The effects of wing shape and flapping characteristics on the thrust generation are studied experimentally. We also demonstrate that the flapping-wing blimp has a significant range advantage over a propeller-based system.

Lighter-Than-Air Autonomous Ball Capture and Scoring Robot -- Design, Development, and Deployment

This paper describes the full end-to-end design of our primary scoring agent in an aerial autonomous robotics competition from April 2023. As open-ended robotics competitions become more popular, we wish to begin documenting successful team designs and approaches. The intended audience of this paper is not only any future or potential participant in this particular national Defend The Republic (DTR) competition, but rather anyone thinking about designing their first robot or system to be entered in a competition with clear goals. Future DTR participants can and should either build on the ideas here, or find new alternate strategies that can defeat the most successful design last time. For non-DTR participants but students interested in robotics competitions, identifying the minimum viable system needed to be competitive is still important in helping manage time and prioritizing tasks that are crucial to competition success first.

Target Defense against Sequentially Arriving Intruders

We consider a variant of the target defense problem where a single defender is tasked to capture a sequence of incoming intruders. The intruders' objective is to breach the target boundary without being captured by the defender. As soon as the current intruder breaches the target or gets captured by the defender, the next intruder appears at a random location on a fixed circle surrounding the target. Therefore, the defender's final location at the end of the current game becomes its initial location for the next game. Thus, the players pick strategies that are advantageous for the current as well as for the future games. Depending on the information available to the players, each game is divided into two phases: partial information and full information phase. Under some assumptions on the sensing and speed capabilities, we analyze the agents' strategies in both phases. We derive equilibrium strategies for both the players to optimize the capture percentage using the notions of engagement surface and capture circle. We quantify the percentage of capture for both finite and infinite sequences of incoming intruders.

Defending a Perimeter from a Ground Intruder Using an Aerial Defender: Theory and Practice

The perimeter defense game has received interest in recent years as a variant of the pursuit-evasion game. A number of previous works have solved this game to obtain the optimal strategies for defender and intruder, but the derived theory considers the players as point particles with first-order assumptions. In this work, we aim to apply the theory derived from the perimeter defense problem to robots with realistic models of actuation and sensing and observe performance discrepancy in relaxing the first-order assumptions. In particular, we focus on the hemisphere perimeter defense problem where a ground intruder tries to reach the base of a hemisphere while an aerial defender constrained to move on the hemisphere aims to capture the intruder. The transition from theory to practice is detailed, and the designed system is simulated in Gazebo. Two metrics for parametric analysis and comparative study are proposed to evaluate the performance discrepancy.

Perimeter-defense Game between Aerial Defender and Ground Intruder

We study a variant of pursuit-evasion game in the context of perimeter defense. In this problem, the intruder aims to reach the base plane of a hemisphere without being captured by the defender, while the defender tries to capture the intruder. The perimeter-defense game was previously studied under the assumption that the defender moves on a circle. We extend the problem to the case where the defender moves on a hemisphere. To solve this problem, we analyze the strategies based on the breaching point at which the intruder tries to reach the target and predict the goal position, defined as optimal breaching point, that is achieved by the optimal strategies on both players. We provide the barrier that divides the state space into defender-winning and intruder-winning regions and prove that the optimal strategies for both players are to move towards the optimal breaching point. Simulation results are presented to demonstrate that the optimality of the game is given as a Nash equilibrium.

Minimal Exposure Dubins Orienteering Problem

Different applications, such as environmental monitoring and military operations, demand the observation of predefined target locations, and an autonomous mobile robot can assist in these tasks. In this context, the Orienteering Problem (OP) is a well-known routing problem, in which the goal is to maximize the objective function by visiting the most rewarding locations, however, respecting a limited travel budget (e.g., length, time, energy). However, traditional formulations for routing problems generally neglect some environment peculiarities, such as obstacles or threatening zones. In this paper, we tackle the OP considering Dubins vehicles in the presence of a known deployed sensor field. We propose a novel multi-objective formulation called Minimal Exposure Dubins Orienteering Problem (MEDOP), whose main objectives are: (i) maximize the collected reward, and (ii) minimize the exposure of the agent, i.e., the probability of being detected. The solution is based on an evolutionary algorithm that iteratively varies the subset and sequence of locations to be visited, the orientations on each location, and the turning radius used to determine the paths. Results show that our approach can efficiently find a diverse set of solutions that simultaneously optimize both objectives.

Decentralization of Multiagent Policies by Learning What to Communicate

Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication to be manually defined by an expert; this is true regardless of whether the behaviors themselves are bespoke, optimization based, or learned. We present an agent architecture and training methodology using neural networks to learn task-oriented communication semantics based on the example of a communication-unaware expert policy. A perimeter defense game illustrates the system's ability to handle dynamically changing numbers of agents and its graceful degradation in performance as communication constraints are tightened or the expert's observability assumptions are broken.