When independently trained or designed robots are deployed in a shared environment, their combined actions can lead to unintended negative side effects (NSEs). To ensure safe and efficient operation, robots must optimize task performance while minimizing the penalties associated with NSEs, balancing individual objectives with collective impact. We model the problem of mitigating NSEs in a cooperative multi-agent system as a bi-objective lexicographic decentralized Markov decision process. We assume independence of transitions and rewards with respect to the robots' tasks, but the joint NSE penalty creates a form of dependence in this setting. To improve scalability, the joint NSE penalty is decomposed into individual penalties for each robot using credit assignment, which facilitates decentralized policy computation. We empirically demonstrate, using mobile robots and in simulation, the effectiveness and scalability of our approach in mitigating NSEs. Code: https://tinyurl.com/RECON-NSE-Mitigation

Small quadrotor UAVs are projected to fly increasingly in urban environments for a wide variety of applications such as disaster response, police surveillance, civil infrastructure inspection, and air quality measurement. Micro UAVs can detect and avoid obstacles using onboard cameras; nevertheless, disturbances such as wind gusts, operator error, or failure of onboard vision can still result in dangerous collisions with objects. In the urban setting, the most predominant obstacles are walls and poles. With the aim of developing collision recovery control solutions for quadrotor UAVs, this paper investigates the collision dynamics between a propeller-protected quadrotor UAV and a vertical pole. Simulations provide insight into a quadrotor's post-collision dynamics and experimental trials demonstrate the feasibility of autonomously recovering to stable flight using only inertial onboard sensing in real-time.