基于强化学习的视觉引导户外飞行与避障
Vision-Guided Outdoor Flight and Obstacle Evasion via Reinforcement Learning
AI总结：
提出一种基于立体视觉深度和视觉惯性里程计的传感器运动策略，通过强化学习和特权学习在仿真中训练，实现零样本迁移到未知户外环境和无人机平台进行自主避障导航。
摘要：
尽管四旋翼飞行器凭借其全向机动性拥有令人印象深刻的穿越能力，但在复杂环境中需要持续的人工操控限制了其在GNSS和遥测信号缺失场景中的应用。为此，我们提出了一种新颖的传感器运动策略，该策略使用立体视觉深度和视觉惯性里程计（VIO）在未知环境中自主穿越障碍物以到达目标点。该策略由一个预训练的自编码器作为感知前端，后接一个规划与控制LSTM网络，输出速度指令，可由现成的商用无人机执行。我们利用强化学习和特权学习范式，通过两阶段过程在仿真中训练该策略：1）以全局运动规划器生成的优化轨迹作为监督骨干进行初始训练；2）在课程环境中进一步微调。为弥合仿真到现实的差距，我们采用领域随机化和奖励塑造来创建对噪声和领域偏移具有鲁棒性的策略。在户外实验中，我们的方法成功实现了对训练中从未遇到的障碍环境和无人机平台的零样本迁移。
英文摘要：
Although quadcopters boast impressive traversal capabilities enabled by their omnidirectional maneuverability, the need for continuous pilot control in complex environments impedes their application in GNSS and telemetry-denied scenarios. To this end, we propose a novel sensorimotor policy that uses stereo-vision depth and visual-inertial odometry (VIO) to autonomously navigate through obstacles in an unknown environment to reach a goal point. The policy is comprised of a pre-trained autoencoder as the perception head followed by a planning and control LSTM network which outputs velocity commands that can be followed by an off-the-shelf commercial drone. We leverage reinforcement and privileged learning paradigms to train the policy in simulation through a two-stage process: 1) initial training with optimal trajectories generated by a global motion planner acting as a supervisory backbone, 2) further fine-tuning in a curriculum environment. To bridge the sim-to-real gap, we employ domain randomization and reward shaping to create a policy that is both robust to noise and domain shift. In outdoor experiments, our approach achieves successful zero-shot transfer to both obstacle environments and a drone platform that were never encountered during training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
