Navigation has been classically solved in robotics through the combination of SLAM and planning. More recently, beyond waypoint planning, problems involving significant components of (visual) high-level reasoning have been explored in simulated environments, mostly addressed with large-scale machine learning, in particular RL, offline-RL or imitation learning. These methods require the agent to learn various skills like local planning, mapping objects and querying the learned spatial representations. In contrast to simpler tasks like waypoint planning (PointGoal), for these more complex tasks the current state-of-the-art models have been thoroughly evaluated in simulation but, to our best knowledge, not yet in real environments. In this work we focus on sim2real transfer. We target the challenging Multi-Object Navigation (Multi-ON) task and port it to a physical environment containing real replicas of the originally virtual Multi-ON objects. We introduce a hybrid navigation method, which decomposes the problem into two different skills: (1) waypoint navigation is addressed with classical SLAM combined with a symbolic planner, whereas (2) exploration, semantic mapping and goal retrieval are dealt with deep neural networks trained with a combination of supervised learning and RL. We show the advantages of this approach compared to end-to-end methods both in simulation and a real environment and outperform the SOTA for this task.

翻译：导航问题在机器人学中传统上通过同时定位与地图构建（SLAM）与规划相结合解决。近年来，除路径点规划外，涉及高层（视觉）推理的复杂问题已在模拟环境中得到探索，主要采用大规模机器学习方法，特别是强化学习（RL）、离线强化学习或模仿学习。这些方法要求智能体掌握局部规划、目标物体映射及查询所学空间表征等多种技能。与路径点规划（PointGoal）等简单任务不同，当前最先进的复杂任务模型虽已在仿真中经过充分评估，但据我们所知尚未在真实环境中验证。本研究聚焦于仿真到现实（sim2real）的迁移。我们针对具有挑战性的多目标导航（Multi-ON）任务，将其部署到包含原始虚拟Multi-ON物体真实复刻品的物理环境中。我们提出一种混合导航方法，将问题分解为两种不同技能：（1）路径点导航采用经典SLAM结合符号规划器实现；（2）探索、语义建图与目标检索则通过监督学习与强化学习联合训练的深度神经网络处理。我们展示了该方法相较于端到端方法在仿真与真实环境中的优势，并超越了该任务当前的最优性能（SOTA）。