Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning

Abstract

This paper focuses on inverse reinforcement learning for autonomous navigation using distance and semantic category observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory. We develop a map encoder, that infers semantic category probabilities from the observation sequence, and a cost encoder, defined as a deep neural network over the semantic features. Since the expert cost is not directly observable, the model parameters can only be optimized by differentiating the error between demonstrated controls and a control policy computed from the cost estimate. We propose a new model of expert behavior that enables error minimization using a closed-form subgradient computed only over a subset of promising states via a motion planning algorithm. Our approach allows generalizing the learned behavior to new environments with new spatial configurations of the semantic categories. We analyze the different components of our model in a minigrid environment. We also demonstrate that our approach learns to follow traffic rules in the autonomous driving CARLA simulator by relying on semantic observations of buildings, sidewalks, and road lanes.

arXiv comment16 pages, 12 figures. arXiv admin note: text overlap with arXiv:2006.05043

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Group Equivariant Convolutional Networks
• Reinforcement Learning with Deep Energy-Based Policies
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
• Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks
• Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods
• SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
• Memory Augmented Control Networks

Cited by in corpus (1)

• Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning