面向自主机器人快速强化学习导航的无渲染事件帧模拟
Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation
Dequan Ou · Austin Lopez · Quentin Missinne · Christophe De Wagter · Guido C. H. E. de Croon
中文摘要
事件相机具有低延迟、高动态范围及毫瓦级功耗，适合小型无人机在杂乱环境中导航。现有模拟器通常先渲染逼真图像再转换为事件，导致大规模强化学习速度过慢。该研究提出一种解析事件模拟器，利用事件相机测量运动对比度边缘的特性，直接从场景几何和自运动合成事件流，无需视觉渲染。该模拟器在单GPU上生成64x64事件观测仅需17微秒，比最先进渲染管线快400倍以上，使目标导向避障的端到端强化学习在30分钟内收敛，比基于渲染事件的训练快三个数量级。策略可零样本迁移至基于物理的事件模拟（Isaac Sim）。在未见过的中等难度杂乱课程（可通行概率约0.57）中，策略达到83%成功率，平均目标速度2.4 m/s；在纹理密集室内大厅中保留70%成功率。策略被量化为1.2 MB的int8网络，部署于配备Prophesee GenX320事件相机和OpenMV N6微控制器的56克Crazyflie无人机上。无需微调、外部处理或定位，在三个难度递增的真实世界障碍课程中，平均成功率为82%（5/5, 5/6, 4/6次飞行）。
关键要点
- 01现有模拟器需先渲染图像再转事件，导致大规模强化学习训练速度过慢。
- 02提出解析事件模拟器，直接从几何和自运动合成事件流，无需视觉渲染。
- 03模拟器生成64x64事件观测仅需17微秒，比最先进渲染管线快400倍以上。
- 04策略在未见过的杂乱课程中达到83%成功率，平均目标速度2.4 m/s。
- 05量化后的1.2 MB int8网络部署于56克Crazyflie无人机，真实世界平均成功率82%。
解读
尚无解读。
原始英文摘要
arXiv:2610.37543v1 Announce Type: new Abstract: Event cameras offer low latency, high dynamic range, and milliwatt-level power consumption, making them ideal for agile robots such as tiny drones navigating through cluttered environments. However, existing simulators generally render photorealistic images before converting them into events, making large-scale reinforcement learning prohibitively slow. We propose an analytic event simulator that exploits what event cameras fundamentally measure - moving contrast edges - to synthesize event streams directly from scene geometry and ego-motion without visual rendering. Our simulator generates a 64x64 event observation in 17 microseconds on a single GPU - over 400x faster than a state-of-the-art rendering pipeline - enabling end-to-end reinforcement learning for goal-directed obstacle avoidance to converge in under 30 minutes - three orders of magnitude faster than training on rendered events. Policies transfer zero-shot to physically based event simulations (ray-traced Isaac Sim). Our policy reaches 83% success in cluttered courses unseen during training (mid-difficulty, traversability probability approx. 0.57), at 2.4 m/s average goal velocity, and retains 70% in a simulated texture-dense indoor hall. Furthermore, we quantized the policy to a 1.2 MB int8 network running fully onboard a 56-gram Crazyflie equipped with a Prophesee GenX320 event camera and an OpenMV N6 microcontroller board. Without any fine-tuning, external processing, or positioning, the policy achieves an average success rate of 82% (5/5, 5/6, 4/6 flights) across three real-world obstacle courses of increasing difficulty. Code: https://github.com/tudelft/rendering-free-event-nav