Learn to Navigate Maplessly with Varied LiDAR Configurations: A Support Point-Based Approach
This work addresses the limitation of fixed sensor configurations in DRL-based mapless navigation, enabling adaptability to different LiDAR setups, which is incremental for robotics and autonomous systems.
The paper tackles the problem of mapless navigation with varied LiDAR configurations by proposing a support point-based DRL model that extracts goal-directed features from obstacle points and selects global features for decision-making, achieving good performance in simulation and real-world experiments, including in crowded scenarios with small obstacles using high-resolution LiDAR.
Deep reinforcement learning (DRL) demonstrates great potential in mapless navigation domain. However, such a navigation model is normally restricted to a fixed configuration of the range sensor because its input format is fixed. In this paper, we propose a DRL model that can address range data obtained from different range sensors with different installation positions. Our model first extracts the goal-directed features from each obstacle point. Subsequently, it chooses global obstacle features from all point-feature candidates and uses these features for the final decision. As only a few points are used to support the final decision, we refer to these points as support points and our approach as support point-based navigation (SPN). Our model can handle data from different LiDAR setups and demonstrates good performance in simulation and real-world experiments. Moreover, it shows great potential in crowded scenarios with small obstacles when using a high-resolution LiDAR.