Multi-Agent Safe Planning with Gaussian Processes

Multi-agent safe systems have become an increasingly important area of study as we can now easily have multiple AI-powered systems operating together. In such settings, we need to ensure the safety of not only each individual agent, but also the overall system. In this paper, we introduce a novel multi-agent safe learning algorithm that enables decentralized safe navigation when there are multiple different agents in the environment. This algorithm makes mild assumptions about other agents and is trained in a decentralized fashion, i. e. with very little prior knowledge about other agents' policies. Experiments show our algorithm performs well with the robots running other algorithms when optimizing various objectives.

Authors

• Zheqing Zhu
• Erdem Biyik
• Dorsa Sadigh

Keywords

• Navigation
• Gaussian processes
• Safety
• Planning
• Intelligent robots
• Gaussian Process
• Learning Algorithms
• Multiple Agents
• Multi-agent Systems
• Environmental Agents
• Safe Navigation
• Time Step
• Upper Bound
• State Space
• Time Complexity
• Number Of Agents
• Reward Function
• Markov Decision Process
• Safety Activity
• High Reward
• Previous Episodes
• Probability 1
• Exploration Strategy
• Unknown Environment
• Collaborative Tasks
• Individual Safety
• State-action Pair
• Safety Constraints