Deep Structured Reactive Planning

An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the behavior of other actors while deciding its own actions as these two processes are inherently intertwined – a vehicle will yield to us if we decide to proceed first at the intersection but will proceed first if we decide to yield. However, this is not captured in most self-driving pipelines, where planning follows prediction. In this paper we propose a novel data-driven, reactive planning objective which allows a self-driving vehicle to jointly reason about its own plans as well as how other actors will react to them. We formulate the problem as an energy-based deep structured model that is learned from observational data and encodes both the planning and prediction problems. Through simulations based on both real-world driving and synthetically generated dense traffic, we demonstrate that our reactive model outperforms a non-reactive variant in successfully completing highly complex maneuvers (lane merges/turns in traffic) faster, without trading off collision rate. Please see our supplementary document https://tinyurl.com/3nukpn5b for all additional details.

Authors

• Jerry Liu
• Wenyuan Zeng
• Raquel Urtasun
• Ersin Yumer

Keywords

• Measurement
• Costs
• Conferences
• Pipelines
• Predictive models
• Data models
• Planning
• Reactive Planning
• Deep Models
• Autonomous Vehicles
• Planning Objectives
• Energy-based Model
• Prediction Model
• Cost Function
• Cross-entropy Loss
• Path Planning
• Goal State
• Partition Function
• Marginal Probability
• Safe Distance
• Future Trajectories
• Neural Net
• Trajectory Prediction
• Lane Change
• Human Drivers
• Interaction Scenarios
• Set Of Costs
• Joint Prediction
• Planning Cost
• Past Trajectories
• Prediction Metrics
• Test Scenarios
• Mean-field
• Polyline
• Predictive Distribution
• Planning Process