Field Navigation Using Fuzzy Elevation Maps Built with Local 3D Laser Scans

Reinforcement and Curriculum Learning for Off-Road Navigation of an UGV with a 3D LiDAR

This paper presents the use of deep Reinforcement Learning (RL) for autonomous navigation of an Unmanned Ground Vehicle (UGV) with an onboard three-dimensional (3D) Light Detection and Ranging (LiDAR) sensor in off-road environments. For training, both the robotic simulator Gazebo and the Curriculum Learning paradigm are applied. Furthermore, an Actor-Critic Neural Network (NN) scheme is chosen with a suitable state and a custom reward function. To employ the 3D LiDAR data as part of the input state of the NNs, a virtual two-dimensional (2D) traversability scanner is developed. The resulting Actor NN has been successfully tested in both real and simulated experiments and favorably compared with a previous reactive navigation approach on the same UGV.

Reactive Navigation on Natural Environments by Continuous Classification of Ground Traversability

Reactivity is a key component for autonomous vehicles navigating on natural terrains in order to safely avoid unknown obstacles. To this end, it is necessary to continuously assess traversability by processing on-board sensor data. This paper describes the case study of mobile robot Andabata that classifies traversable points from 3D laser scans acquired in motion of its vicinity to build 2D local traversability maps. Realistic robotic simulations with Gazebo were employed to appropriately adjust reactive behaviors. As a result, successful navigation tests with Andabata using the robot operating system (ROS) were performed on natural environments at low speeds.

Supervised Learning of Natural-Terrain Traversability with Synthetic 3D Laser Scans

Autonomous navigation of ground vehicles on natural environments requires looking for traversable terrain continuously. This paper develops traversability classifiers for the three-dimensional (3D) point clouds acquired by the mobile robot Andabata on non-slippery solid ground. To this end, different supervised learning techniques from the Python library Scikit-learn are employed. Training and validation are performed with synthetic 3D laser scans that were labelled point by point automatically with the robotic simulator Gazebo. Good prediction results are obtained for most of the developed classifiers, which have also been tested successfully on real 3D laser scans acquired by Andabata in motion.

MIM_SLAM: A Multi-Level ICP Matching Method for Mobile Robot in Large-Scale and Sparse Scenes

In large-scale and sparse scenes, such as farmland, orchards, mines, and substations, 3D simultaneous localization and mapping are challenging matters that need to address issues such as maintaining reliable data association for scarce environmental information and reducing the computational complexity of global optimization for large-scale scenes. To solve these problems, a real-time incremental simultaneous localization and mapping algorithm called MIM_SLAM is proposed in this paper. This algorithm is applied in mobile robots to build a map on a non-flat road with a 3D LiDAR sensor. MIM_SLAM’s main contribution is that multi-level ICP (Iterative Closest Point) matching is used to solve the data association problem, a Fisher information matrix is used to describe the uncertainty of the estimated pose, and these poses are optimized by the incremental optimization method, which can greatly reduce the computational cost. Then, a map with a high consistency will be established. The proposed algorithm has been evaluated in the real indoor and outdoor scenes as well as two substations and benchmarking dataset from KITTI with the characteristics of sparse and large-scale. Results show that the proposed algorithm has a high mapping accuracy and meets the real-time requirements.