Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation

• Main Authors: Kahn, Gregory, Villaflor, Adam, Ding, Bosen, Abbeel, Pieter, Levine, Sergey
• Format: Conference Proceeding
• Language: English
• Subjects: Computational modeling; Learning (artificial intelligence); Navigation; Planning; Prediction algorithms; Robots; Task analysis
• ISSN: 2577-087X
• DOI: 10.1109/ICRA.2018.8460655

Enabling robots to autonomously navigate complex environments is essential for real-world deployment. Prior methods approach this problem by having the robot maintain an internal map of the world, and then use a localization and planning method to navigate through the internal map. However, these approaches often include a variety of assumptions, are computationally intensive, and do not learn from failures. In contrast, learning-based methods improve as the robot acts in the environment, but are difficult to deploy in the real-world due to their high sample complexity. To address the need to learn complex policies with few samples, we propose a generalized computation graph that subsumes value-based model-free methods and model-based methods, with specific instantiations interpolating between model-free and model-based. We then instantiate this graph to form a navigation model that learns from raw images and is sample efficient. Our simulated car experiments explore the design decisions of our navigation model, and show our approach outperforms single-step and N -step double Q-learning. We also evaluate our approach on a real-world RC car and show it can learn to navigate through a complex indoor environment with a few hours of fully autonomous, self-supervised training. Videos of the experiments and code can be found at github.com/gkahn13/gcg.