User-Conditioned Neural Control Policies for Mobile Robotics

TL;DR

This paper introduces a user-conditioned neural control policy for mobile robots, enabling real-time adjustment of behavior such as aggressiveness and speed, demonstrated on quadrotors for efficient, safe, and adaptable flight in simulation and real-world tests.

Contribution

It presents a novel framework using FiLM layers to condition neural control policies on auxiliary inputs, allowing dynamic adjustment during deployment, which was not possible with traditional neural controllers.

Findings

Achieved near time-optimal quadrotor flight at 60 km/h in simulation and real-world.

Enabled real-time regulation of flight aggressiveness through conditioning.

Demonstrated safe, adaptable control in diverse environments.

Abstract

Recently, learning-based controllers have been shown to push mobile robotic systems to their limits and provide the robustness needed for many real-world applications. However, only classical optimization-based control frameworks offer the inherent flexibility to be dynamically adjusted during execution by, for example, setting target speeds or actuator limits. We present a framework to overcome this shortcoming of neural controllers by conditioning them on an auxiliary input. This advance is enabled by including a feature-wise linear modulation layer (FiLM). We use model-free reinforcement-learning to train quadrotor control policies for the task of navigating through a sequence of waypoints in minimum time. By conditioning the policy on the maximum available thrust or the viewing direction relative to the next waypoint, a user can regulate the aggressiveness of the quadrotor's flight during deployment. We demonstrate in simulation and in real-world experiments that a single control policy can achieve close to time-optimal flight performance across the entire performance envelope of the robot, reaching up to 60 km/h and 4.5g in acceleration. The ability to guide a learned controller during task execution has implications beyond agile quadrotor flight, as conditioning the control policy on human intent helps safely bringing learning based systems out of the well-defined laboratory environment into the wild.