Adaptive Monte Carlo localization (AMCL) algorithm has a limited pose accuracy because of the nonconvexity of the laser sensor model, the complex and unstructured features of the working environment, the randomness of particle sampling, and the final pose selection problem. In this paper, an improved AMCL algorithm is proposed, aiming to build a laser radar‐based robot localization system in a complex and unstructured environment, with a LIDAR point cloud scan‐matching process after the particle score calculating process. The weighted mean pose of AMCL particle swarm is used as the initial pose of the scan matching process. The LIDAR point cloud is matched with the probability grid map from coarse to fine using the Gaussian‐Newton method, which results in more accurate poses. Moreover, the scan‐matching pose is added into the particle swarm as a high‐weight particle. So the particle swarm after resampling will be more concentrated in the correct position. The particle filter and the scan‐matching process form a closed loop, thus enhancing the localization accuracy of mobile robots. The experiment results demonstrate that the proposed improved AMCL algorithm is superior to the traditional AMCL algorithm in the complex and unstructured environment, by exploiting the high‐accuracy characteristic of scan matching while inheriting the stability of AMCL.

To realize a robust robotic grasping system for unknown objects in an unstructured environment, large amounts of grasp data and 3D model data for the object are required; the sizes of these data directly affect the rate of successful grasps. To reduce the time cost of data acquisition and labeling and increase the rate of successful grasps, we developed a self-supervised learning mechanism to control grasp tasks performed by manipulators. First, a manipulator automatically collects the point cloud for the objects from multiple perspectives to increase the efficiency of data acquisition. The complete point cloud for the objects is obtained using the hand-eye vision of the manipulator and the truncated signed distance function algorithm. Then, the point cloud data for the objects are used to generate a series of six-degrees-of-freedom grasp poses, and the force-closure decision algorithm is used to add the grasp quality label to each grasp pose to realize the automatic labeling of grasp data. Finally, the point cloud in the gripper closing area corresponding to each grasp pose is obtained and used to train the grasp-quality classification model for the manipulator. The results of performing actual grasping experiments demonstrate that the proposed self-supervised learning method can increase the rate of successful grasps for the manipulator. Note to Practitioners—Most of the existing grasp planning methods of the manipulator are based on public datasets or simulation data to train model algorithms. Owing to the limited types of objects, the limited amount of data in the public datasets, and the lack of real sensor noise in the simulation data, the robustness of the trained algorithm model is insufficient, and it is difficult to apply to unstructured production environments. To solve the above problems, we propose a 6-DOF capture planning method based on self-supervised learning and introduce a self-supervised learning mechanism to solve the problem of grasp data acquisition in real scenes. The manipulator automatically collects object data from multiple perspectives, performs desktop-level 3D reconstruction, and finally uses the force-closure decision algorithm to automatically label the data in order to realize automatic acquisition and labeling of the grasp data in a real scenario. Preliminary experiments show that this method can obtain high-quality grasp data and can be applied to grasp operations in real multi-target and cluttered environments. However, it has not been tested in actual production environments. This paper focuses on the data acquisition module in the 6-DOF grasp planning framework. In future research, we will design a more efficient grasp planning module to improve the grasp efficiency of the manipulator.

To improve the efficiency of deep reinforcement learning (DRL)-based methods for robot manipulator trajectory planning in random working environments, we present three dense reward functions. These rewards differ from the traditional sparse reward. First, a posture reward function is proposed to speed up the learning process with a more reasonable trajectory by modeling the distance and direction constraints, which can reduce the blindness of exploration. Second, a stride reward function is proposed to improve the stability of the learning process by modeling the distance and movement distance of joint constraints. Finally, in order to further improve learning efficiency, we are inspired by the cognitive process of human behavior and propose a stage incentive mechanism, including a hard-stage incentive reward function and a soft-stage incentive reward function. Extensive experiments show that the soft-stage incentive reward function is able to improve the convergence rate, get higher mean reward and lower standard deviation after convergence.

Considering the adverse impact of speed measurement on the accuracy of pose estimation after a mobile robot slips, collides, or abducts, this paper proposes a monocular inertial simultaneous localization and mapping algorithm that includes wheel speed anomaly detection. The algorithm adds wheel speed measurement to the least squares problem in a tightly coupled manner and uses a nonlinear optimization method to maximize the posterior probability to solve the optimal state estimation. For the speed control of the Mecanum wheel, because the existing closed-loop speed control method cannot calculate the motion constraint error, this paper reports a design of a control method of the Mecanum wheel moving chassis based on torque control, which can use the motion constraint error to estimate the credibility of the wheel speed measurement to detect whether the chassis movement status is abnormal; meanwhile, to prevent the chassis speed measurement error from adversely affecting the robot pose estimation, this paper uses three methods to actively detect whether the chassis movement is abnormal, and analyze the chassis movement status in real time. When it is determined that the chassis has abnormal motion, the wheel odometer pre-integration measurement of the current frame is actively removed from the state estimation equation, thereby ensuring the accuracy of the pose estimation. Experimental results show the feasibility and effectiveness of the method proposed in this paper, and the algorithm is robust.

For the existing visual–inertial SLAM algorithm, when the robot is moving at a constant speed or purely rotating and encounters scenes with insufficient visual features, problems of low accuracy and poor robustness arise. Aiming to solve the problems of low accuracy and robustness of the visual inertial SLAM algorithm, a tightly coupled vision-IMU-2D lidar odometry (VILO) algorithm is proposed. Firstly, low-cost 2D lidar observations and visual–inertial observations are fused in a tightly coupled manner. Secondly, the low-cost 2D lidar odometry model is used to derive the Jacobian matrix of the lidar residual with respect to the state variable to be estimated, and the residual constraint equation of the vision-IMU-2D lidar is constructed. Thirdly, the nonlinear solution method is used to obtain the optimal robot pose, which solves the problem of how to fuse 2D lidar observations with visual–inertial information in a tightly coupled manner. The results show that the algorithm still has reliable pose-estimation accuracy and robustness in many special environments, and the position error and yaw angle error are greatly reduced. Our research improves the accuracy and robustness of the multi-sensor fusion SLAM algorithm.