Behavior cloning improves autonomous driving from bird's-eye view

Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities

RoboticsMachine Learning

Summary

Getting self-driving cars to follow traffic lights correctly can be really hard, especially when there are only a few examples for the car to learn from. The authors worked on this problem by teaching a computer to copy expert drivers using overhead views of the road. They gave more attention to rare but important actions, like stopping at red lights, by weighting those examples higher during training. Their approach helped cars complete more driving routes correctly in a driving simulator, even in new, unseen cities.

What this means in practice

  • For autonomous vehicle developers: Improve training of self-driving car policies from limited expert examples to better handle rare but critical driving actions like traffic light compliance.
  • For robotics system engineers: Use bird's-eye view inputs to simplify control policy learning in complex navigation tasks with few expert demonstrations.

Authors

Eric Aislan Antonelo, Gustavo Claudio Karl Couto, Christian Möller, Pedro Henrique Fernandes

Abstract

This paper investigates the use of Behavior Cloning (BC) for autonomous driving from a bird's-eye view (BEV) perspective in simulated urban environments. BC uses supervised learning to mimic expert driving behaviors. Previous works have applied BC in the CARLA simulator but did not fully address the challenges of traffic light compliance. Our approach enhances BC by integrating a kernel density estimator to adjust training sample weights based on action density, thereby improving the learning of rare but critical actions such as stopping at red lights and accelerating at green lights, specially in scenarios of scarce number of expert demonstrations. Using BEV inputs, which provide an abstract top-down view of the driving environment, our method simplifies the policy learning process. The trained convolutional neural network (CNN) outputs steering and acceleration actions based on these BEV inputs and additional state variables. Experimental results in the CARLA simulator demonstrate that our weighted BC method significantly improves driving performance, achieving higher route completion compared to standard BC. This weighted approach proved to be crucial in learning correct driving behaviors, particularly in test environments not encountered during training, highlighting its potential for enhancing autonomous vehicle navigation.