Learning to navigate through crowded environments

The goal of this research is to enable mobile robots to navigate through crowded environments such as indoor shopping malls, airports, or downtown side walks. The key research question addressed in this paper is how to learn planners that generate human-like motion behavior. Our approach uses inverse reinforcement learning (IRL) to learn human-like navigation behavior based on example paths. Since robots have only limited sensing, we extend existing IRL methods to the case of partially observable environments. We demonstrate the capabilities of our approach using a realistic crowd flow simulator in which we modeled multiple scenarios in crowded environments. We show that our planner learned to guide the robot along the flow of people when the environment is crowded, and along the shortest path if no people are around.

Authors

• Peter Henry
• Christian Vollmer
• Brian Ferris
• Dieter Fox

Keywords

• Navigation
• Learning
• Cost function
• Mobile robots
• Airports
• Robot sensing systems
• Gaussian processes
• Robotics and automation
• USA Councils
• Computer science
• Crowded Environment
• Research Goals
• Shortest Path
• Mobile Robot
• Inverse Reinforcement Learning
• Human-like Behavior
• Time Step
• Dynamic Characteristics
• Pedestrian
• Grid Cells
• Gaussian Process
• Traffic Flow
• Path Planning
• Markov Decision Process
• Coordinate Plane
• Characteristic Velocity
• Laser Ranging
• Robot Operating System
• Density Of People
• Probable Path
• Cost Path
• Linear Combination Of Features
• Planning Techniques
• Robot Sensors
• Cost Weight
• Feature Counts
• Process Model
• Training Data