Fast Obstacle Avoidance Based on Real-Time Sensing

Humans excel at navigating and moving through dynamic and complex spaces, such as crowded streets. For robots to do the same, it is crucial that they are endowed with highly reactive obstacle avoidance which is adept at partial and poor sensing. We address the issue of enabling obstacle avoidance based on sparse and asynchronous perception. The proposed control scheme combines a high-level input command provided by either a planner or a human operator with fast reactive obstacle avoidance (FOA). The sampling-based sensor data can be combined with an analytical reconstruction of the obstacles for real-time collision avoidance. Thus, we can ensure that the agent does not become stuck when a feasible path exists between obstacles. Our algorithm was evaluated experimentally on static laser data from cluttered, indoor office environments. Additionally, it was used in shared-control mode in a dynamic and complex outdoor environment in the center of Lausanne. The proposed control scheme successfully avoided collisions in both scenarios. During the experiments, the controller took 1 ms to evaluate over 30000 data points.

Automated summary

In order for robots to navigate through crowded spaces like humans, they need highly reactive obstacle avoidance that can handle partial and poor sensing. Our proposed control scheme combines high-level input commands with fast reactive obstacle avoidance (FOA) to enable obstacle avoidance based on sparse and asynchronous perception. By analyzing sampled sensor data and reconstructing obstacles in real time, the algorithm ensures that the agent does not get stuck when a feasible path exists between obstacles. The algorithm was successfully evaluated in cluttered indoor office environments and in a dynamic outdoor environment in Lausanne.