XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees

We present a novel sensor-based learning navigation algorithm to compute a collision-free trajectory for a robot in dense and dynamic environments with moving obstacles or targets. Our approach uses deep reinforcement learning-based expert policy that is trained using a sim2real paradigm. In order to increase the reliability and handle the failure cases of the expert policy, we combine with a policy extraction technique to transform the resulting policy into a decision tree format. We use properties of decision trees to analyze and modify the policy and improve performance of navigation algorithm including smoothness, frequency of oscillation, frequency of immobilization, and obstruction of target. Overall, we are able to modify the policy to design an improved learning algorithm without retraining. We highlight the benefits of our approach in simulated environments and navigating a Clearpath Jackal robot among moving pedestrians. (Videos at this url: https://gamma.umd.edu/researchdirections/xrl/navviper)

Authors

• Aaron M. Roth
• Jing Liang 0006
• Dinesh Manocha

Keywords

• Navigation
• Heuristic algorithms
• Transforms
• Robot sensing systems
• Trajectory
• Decision trees
• Reliability
• Decision Tree
• Robot Navigation
• Expert Policy
• Collision
• Deep Learning
• Path Length
• State Space
• Pedestrian
• Deep Reinforcement Learning
• Binary Tree
• Discrete Action
• Neural Net
• Dense Environments
• Imitation Learning
• Total Path Length
• Deep Reinforcement Learning Method
• Dynamic Obstacles
• Navigation Algorithm
• Neural Network
• Complex Environment
• Linear Velocity
• Occupancy Grid
• Leaf Node
• Reward Function
• Left Rotation
• Random Locations
• State St
• Tuning Parameter
• Goal Position
• Problem Setup