Autonomous mobile robots have been used in outdoor delivery services. Delivery robots have to cope with dynamic obstacles and various environmental conditions. Although several successful technological solutions are available for indoor applications, there are still plenty of unsolved problems in outdoor environments. In this study, we concentrate on three technological challenges hindering the development of campus delivery robots. The first challenge is robust localization in various dynamic outdoor environments. Localization results obtained using lidars and Global Navigation Satellite System (GNSS) sensors show complementary advantages and disadvantages. The proposed localization strategy efficiently combines information from multiple sensors. The second challenge is safe navigation based on the detection of the traversable region. The presented terrain traversability analysis provides clear, real-time positive and negative obstacle information. The third challenge is the requirement of an effective path planning strategy to reduce the risk of collisions or deadlocks. We collected the appearance history of regional dynamic obstacles in the map. The resultant path was carefully generated to avoid crowded areas. Experimental verifications have been successfully conducted on the Korea University campus. The presented results clearly indicate that the proposed methods are essential to achieve safe and reliable navigation in dynamic, real-world environments.
12 March 2024 in IEEE Robotics and Automation Letters
Mobile robots operating in outdoor environments face the challenge of navigating various terrains with different degrees of difficulty. Therefore, traversability estimation is crucial for safe and efficient robot navigation. Current approaches utilize a robot's driving experience to learn traversability in a self-supervised fashion. However, providing sufficient and diverse experience to the robot is difficult in many practical applications. In this paper, we propose a self-supervised traversability learning method that adapts to challenging terrains with limited prior experience. One key aspect is to enable prioritized learning of scarce yet high-risk terrains by using a risk-sensitive approach. To this end, we train a neural network through a risk-aware instance weighting scheme. Another key aspect is to leverage traversability pseudo-labels on the basis of a self-training scheme. The proposed confidence-regularized self-training generates high-quality pseudo-labels, thereby achieving reliable data augmentation for unexperienced terrains. The effectiveness of the proposed method is verified in extensive real-world experiments, ranging from structured urban environments to complex rugged terrains.
Multi-Agent Path Finding (MAPF) is a core technology for logistics automation in factories and warehouses. Guidance-based approaches that reflect the structural properties of factory environments have been widely adopted for computational efficiency and execution feasibility. However, these approaches generally assume static environments in which predefined guidance policies remain valid. Therefore, unexpected obstacles can cause inter-robot collisions or deadlocks. To make nominal MAPF plans robust against execution uncertainty, prior studies have incorporated bounded execution delays into MAPF. A representative method is k Robust Multi-Agent Path Finding (kR-MAPF), which models allowable execution delay using a global robustness parameter k. However, when large obstacle-induced delays are represented by a single global robustness parameter, kR-MAPF imposes unnecessary conservatism and increases the search space. This increase in search space raises planning runtime and reduces path efficiency in large-scale robot fleet operation. This paper proposes a multi-robot path planning framework that updates guidance policies for each segment based on real-time obstacle information. The proposed framework identifies robots affected by obstacles and selectively replans their paths, thereby reducing unnecessary computation while maintaining path planning success and path efficiency. Simulation results in a factory environment with up to 100 robots demonstrate that the proposed framework maintains a 100% success rate under all tested conditions. Compared with kR-MAPF with different values of k, the proposed framework reduces planning runtime by approximately 35–79% and flowtime by approximately 7–24%. These results demonstrate that obstacle-aware selective replanning can improve both real-time performance and path efficiency in dynamic factory environments. The proposed framework provides a technical basis for stable large-scale multi-robot operation in structured industrial environments.