Navigating Congested Environments with Risk Level Sets

In this paper, we address the problem of navigating in a cluttered environment by introducing a congestion cost that maps the density and motion of objects to an occupancy risk. We propose that an agent can choose a “risk level set” from this cost function and construct a planning space from this set. In choosing different levels of risk, the agent adjusts its interactions with the other agents. From the assumption that agents are self-preserving, we show that any agent planning within their risk level set will avoid collisions with other agents. We then present an application of planning with risk level sets in the framework of an autonomous vehicle driving along a highway. Using the risk level sets, the agent can determine safe zones when planning a sequence of lane changes. Through simulations in Matlab, we demonstrate how the choice of risk threshold manifests as aggressive or conservative behavior.

Authors

• Alyssa Pierson
• Wilko Schwarting
• Sertac Karaman
• Daniela Rus

Keywords

• Planning
• Level set
• Navigation
• Vehicle dynamics
• Autonomous vehicles
• Collision avoidance
• Cost function
• Risk Level
• Congested Environment
• Aggressive Behavior
• Sequence Changes
• Risk Threshold
• Lane Change
• Framework Set
• Different Levels Of Risk
• Conservation Behavior
• Cluttered Environments
• Congestion Costs
• Optimal Control
• Travel Time
• Maximum Speed
• Maximum Velocity
• Traffic Congestion
• Environmental Agents
• Planning Horizon
• Congestion Level
• Agent System
• Environmental Density
• Maximum Acceleration
• Multi-agent Systems
• Planning Algorithm
• Dynamic Obstacles
• Multiple Agents