Environment as Policy: Learning to Race in Unseen Tracks

Reinforcement learning (RL) has achieved outstanding success in complex robot control tasks, such as drone racing, where the RL agents have outperformed human champions in a known racing track. However, these agents fail in unseen track configurations, always requiring complete retraining when presented with new track layouts. This work aims to develop RL agents that generalize effectively to novel track configurations without retraining. The naive solution of training directly on a diverse set of track layouts can overburden the agent, resulting in suboptimal policy learning as the increased complexity of the environment impairs the agent's ability to learn to fly. To enhance the generalizability of the RL agent, we propose an adaptive environment-shaping framework that dynamically adjusts the training environment based on the agent's performance. We achieve this by leveraging a secondary RL policy to design environments that strike a balance between being challenging and achievable, allowing the agent to adapt and improve progressively. Using our adaptive environment shaping, one single racing policy efficiently learns to race in diverse challenging tracks. Experimental results validated in both simulation and the real world show that our method enables drones to successfully fly complex and unseen race tracks, outperforming existing environment-shaping techniques. Project page: http://rpg.ifi.uzh.ch/env_as_policy/index.html

Demonstrating Agile Flight from Pixels without State Estimation

Quadrotors are among the most agile flying robots. Despite recent advances in learning-based control and computer vision, autonomous drones still rely on explicit state estimation. On the other hand, human pilots only rely on a first-person-view video stream from the drone onboard camera to push the platform to its limits and fly robustly in unseen environments. To the best of our knowledge, we present the first vision-based quadrotor system that autonomously navigates through a sequence of gates at high speeds while directly mapping pixels to control commands. Like professional drone-racing pilots, our system does not use explicit state estimation and leverages the same control commands humans use (collective thrust and body rates). We demonstrate agile flight at speeds up to 40km/h with accelerations up to 2g. This is achieved by training vision-based policies with reinforcement learning (RL). The training is facilitated using an asymmetric actor-critic with access to privileged information. To overcome the computational complexity during image-based RL training, we use the inner edges of the gates as a sensor abstraction. This simple yet robust, task-relevant representation can be simulated during training without rendering images. During deployment, a Swin-transformer-based gate detector is used. Our approach enables autonomous agile flight with standard, off-the-shelf hardware. Although our demonstration focuses on drone racing, we believe that our method has an impact beyond drone racing and can serve as a foundation for future research into real-world applications in structured environments.

Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight

We combine the effectiveness of Reinforcement Learning (RL) and the efficiency of Imitation Learning (IL) in the context of vision-based, autonomous drone racing. We focus on directly processing visual input without explicit state estimation. While RL offers a general framework for learning complex controllers through trial and error, it faces challenges regarding sample efficiency and computational demands due to the high dimensionality of visual inputs. Conversely, IL demonstrates efficiency in learning from visual demonstrations but is limited by the quality of those demonstrations and faces issues like covariate shift. To overcome these limitations, we propose a novel training framework combining RL and IL's advantages. Our framework involves three stages: initial training of a teacher policy using privileged state information, distilling this policy into a student policy using IL, and performance-constrained adaptive RL fine-tuning. Our experiments in both simulated and real-world environments demonstrate that our approach achieves superior performance and robustness than IL or RL alone in navigating a quadrotor through a racing course using only visual information without explicit state estimation.

Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight

Scene transfer for vision-based mobile robotics applications is a highly relevant and challenging problem. The utility of a robot greatly depends on its ability to perform a task in the real world, outside of a well-controlled lab environment. Existing scene transfer end-to-end policy learning approaches often suffer from poor sample efficiency or limited generalization capabilities, making them unsuitable for mobile robotics applications. This work proposes an adaptive multi-pair contrastive learning strategy for visual representation learning that enables zero-shot scene transfer and real-world deployment. Control policies relying on the embedding are able to operate in unseen environments without the need for finetuning in the deployment environment. We demonstrate the performance of our approach on the task of agile, vision-based quadrotor flight. Extensive simulation and real-world experiments demonstrate that our approach successfully generalizes beyond the training domain and outperforms all baselines.

Autonomous Power Line Inspection with Drones via Perception-Aware MPC

Drones have the potential to revolutionize power line inspection by increasing productivity, reducing inspection time, improving data quality, and eliminating the risks for human operators. Current state-of-the-art systems for power line inspection have two shortcomings: (i) control is decoupled from perception and needs accurate information about the location of the power lines and masts; (ii) collision avoidance is decoupled from the power line tracking, which results in poor tracking in the vicinity of the power masts, and, consequently, in decreased data quality for visual inspection. In this work, we propose a model predictive controller (MPC) that overcomes these limitations by tightly coupling perception and action. Our controller generates commands that maximize the visibility of the power lines while, at the same time, safely avoiding the power masts. For power line detection, we propose a lightweight learning-based detector that is trained only on synthetic data and is able to transfer zero-shot to real-world power line images. We validate our system in simulation and real-world experiments on a mock-up power line infrastructure.

See Yourself in Others: Attending Multiple Tasks for Own Failure Detection

Autonomous robots deal with unexpected scenarios in real environments. Given input images, various visual perception tasks can be performed, e.g., semantic segmentation, depth estimation and normal estimation. These different tasks provide rich information for the whole robotic perception system. All tasks have their own characteristics while sharing some latent correlations. However, some of the task predictions may suffer from the unreliability dealing with complex scenes and anomalies. We propose an attention-based failure detection approach by exploiting the correlations among multiple tasks. The proposed framework infers task failures by evaluating the individual prediction, across multiple visual perception tasks for different regions in an image. The formulation of the evaluations is based on an attention network supervised by multi-task uncertainty estimation and their corresponding prediction errors. Our proposed framework generates more accurate estimations of the prediction error for the different task's predictions.