YOPOv2-Tracker: An End-to-End Agile Tracking and Navigation Framework from Perception to Action

TL;DR

This paper introduces YOPOv2-Tracker, an end-to-end framework that directly maps sensory inputs to control commands for quadrotors, reducing latency and improving agility in complex environments.

Contribution

It presents a novel integrated deep learning approach that combines traditional motion planning with end-to-end control, eliminating the need for separate modules and expert demonstrations.

Findings

Effective real-world performance in forest and building environments

Reduced latency and increased agility compared to traditional pipelines

Seamless integration of traditional planning with deep learning

Abstract

Traditional target tracking pipelines including detection, mapping, navigation, and control are comprehensive but introduce high latency, limitting the agility of quadrotors. On the contrary, we follow the design principle of "less is more", striving to simplify the process while maintaining effectiveness. In this work, we propose an end-to-end agile tracking and navigation framework for quadrotors that directly maps the sensory observations to control commands. Importantly, leveraging the multimodal nature of navigation and detection tasks, our network maintains interpretability by explicitly integrating the independent modules of the traditional pipeline, rather than a crude action regression. In detail, we adopt a set of motion primitives as anchors to cover the searching space regarding the feasible region and potential target. Then we reformulate the trajectory optimization as regression of primitive offsets and associated costs considering the safety, smoothness, and other metrics. For tracking task, the trajectories are expected to approach the target and additional objectness scores are predicted. Subsequently, the predictions, after compensation for the estimated lumped disturbance, are transformed into thrust and attitude as control commands for swift response. During training, we seamlessly integrate traditional motion planning with deep learning by directly back-propagating the gradients of trajectory costs to the network, eliminating the need for expert demonstration in imitation learning and providing more direct guidance than reinforcement learning. Finally, we deploy the algorithm on a compact quadrotor and conduct real-world validations in both forest and building environments to demonstrate the efficiency of the proposed method.