Active Exploration for Obstacle Detection on a Mobile Humanoid Robot

Abstract

Conventional approaches to robot navigation in unstructured environments rely on information acquired from the LiDAR mounted on the robot base to detect and avoid obstacles. This approach fails to detect obstacles that are too small, or that are invisible because they are outside the LiDAR’s field of view. A possible strategy is to integrate information from other sensors. In this paper, we explore the possibility of using depth information from a movable RGB-D camera mounted on the head of the robot, and investigate, in particular, active control strategies to effectively scan the environment. Existing works combine RGBD-D and 2D LiDAR data passively by fusing the current point-cloud from the RGB-D camera with the occupancy grid computed from the 2D LiDAR data, while the robot follows a given path. In contrast, we propose an optimization strategy that actively changes the position of the robot’s head, where the camera is mounted, at each point of the given navigation path; thus, we can fully exploit the RGB-D camera to detect, and hence avoid, obstacles undetected by the 2D LiDAR, such as overhanging obstacles or obstacles in blind spots. We validate our approach in both simulation environments to gather statistically significant data and real environments to show the applicability of our method to real robots. The platform used is the humanoid robot R1.

Tour guide robot: a 5G-enabled robot museum guide

“…A YARP node was implemented that, given the planned trajectory for the robot, moves the head so as to look ahead at the next point on the trajectory that lies on a circle of a given radius around the robot frame. This helps mitigate the narrow field of view of the camera when the robot is turning and more in general helps detecting dynamic 3D obstacles that are above the laser range finder and on the robot’s path during movement ( Nobile et al, 2021 ).…”

MoDeT: a low-cost obstacle tracker for self-driving mobile robot navigation using 2D-laser scan

“…An obstacle avoidance, including visual-based detection and control, is presented in Wenzel et al (2021). And in Nobile et al (2021), an RGB-D camera is used to detect small objects that are invisible in the field of view (FOV) of light detection and ranging (LiDAR) sensors. However, the camera is easily affected by lighting conditions in the environment, and the FOV of the camera is also one challenge to track obstacles around the AMR.…”

“…However, this sector division method may ignore optimal directions if obstacles only appear in the middle of neighborhood sectors and there are no obstacles near their border. Some other studies presented obstacle detection using the camera, such as Mane and Vhanale (2016), Nadour et al (2019), Skoczen et al (2021), Wenzel et al (2021) and Nobile et al (2021). A real-time obstacle detection and avoidance algorithm using a passive stereoscopic Kinect camera is presented in Mane and Vhanale (2016).…”