Lidar-Based Navigation of Subterranean Environments Using Bio-Inspired Wide-Field Integration of Nearness

Abstract

Navigating unknown environments is an ongoing challenge in robotics. Processing large amounts of sensor data to maintain localization, maps of the environment, and sensible paths can result in high compute loads and lower maximum vehicle speeds. This paper presents a bio-inspired algorithm for efficiently processing depth measurements to achieve fast navigation of unknown subterranean environments. Animals developed efficient sensorimotor convergence approaches, allowing for rapid processing of large numbers of spatially distributed measurements into signals relevant for different behavioral responses necessary to their survival. Using a spatial inner-product to model this sensorimotor convergence principle, environmentally relative states critical to navigation are extracted from spatially distributed depth measurements using derived weighting functions. These states are then applied as feedback to control a simulated quadrotor platform, enabling autonomous navigation in subterranean environments. The resulting outer-loop velocity controller is demonstrated in both a generalized subterranean environment, represented by an infinite cylinder, and nongeneralized environments like tunnels and caves.

Bioinspired Perception and Navigation of Service Robots in Indoor Environments: A Review

“…Additionally, Table 2 displays papers about remote sensing navigation, focusing on LiDAR, laser ranger, and infrared sensors. The tasks include exploration [ 63 , 64 , 66 , 71 ], wheelchair [ 78 ], transport [ 65 , 73 , 74 , 75 ], fire services or search and rescue [ 70 ], floor cleaning [ 68 ], tracking [ 76 ], education [ 72 ], and caring and service [ 79 ]. Some approaches are combined with path planning algorithms, including metaheuristic algorithm, potential field, and A* for navigation [ 66 , 68 , 70 , 78 ].…”

“…Ref. [ 63 ] proposed a bioinspired wide-field integration framework based on sensorimotor convergence with a LiDAR sensor. Its advantage was its computational simplicity and robustness against additive Gaussian sensor noise or occlusions in the measurements.…”

Equal Emphasis on Data and Network: A Two-Stage 3D Point Cloud Object Detection Algorithm with Feature Alignment

“…Owing to its capacity to accurately capture spatial information and generate precise point cloud data, it has garnered significant attention and importance in the field of 3D object detection. With the rise of applications in various fields such as terrain surveying [7][8][9], environmental studies [10][11][12], and more recently, autonomous driving [13][14][15], there has been an increasing demand for robust and accurate 3D object detection systems. LiDAR technology plays a crucial role in meeting this requirement by providing high-resolution point cloud data that can be utilized for object detection, localization, and mapping purposes.…”