Search results

This paper aims to provide a novel obstacle avoidance method based on multi-information inflation map.

In this paper, the multi-information inflation map is introduced, which considers different information, including a two-dimensional grid map and a variety of sensor information. The static layer of the map is pre-processed at first. Then sensor inputs are added in different semantic layers. The processed information in semantic layers is used to update the static layer. The obstacle avoidance algorithm based on the multi-information inflation map is able to generate different avoidance paths for different kinds of obstacles, and the motion planning based on multi-information inflation map can track the global path and drive the robot.

The proposed method was implemented on a self-made mobile robot. Four experiments are conducted to verify the advantages of the proposed method. The first experiment is to demonstrate the advantages of the multi-information inflation map over the layered cost map. The second and third experiments verify the effectiveness of the obstacle avoidance path generation and motion planning. The fourth experiment comprehensively verifies that the obstacle avoidance algorithm is able to deal with different kinds of obstacles.

The multi-information inflation map proposed in this paper has better performance than the layered cost maps. As the static layer is pre-processed, the computational efficiency is higher. Sensor information is added in semantic layers with different cost attenuation coefficients. All layers are reset before next update. Therefore, the previous state will not affect the current situation. The obstacle avoidance and motion planning algorithm based on the multi-information inflation map can generate different paths for different obstacles and drive a robot safely and control the velocity according to different conditions.

The purpose of this paper is to propose a robust iterative LIDAR-based pose tracking method assisted by modified visual odometer to resist initial value disturbance and locate a robot in the environments with certain occlusion.

At first, an iterative LIDAR-based pose tracking method is proposed. The LIDAR information is filtered and occupancy grid map is pre-processed. The sample generation and scoring are iterated so that the result is converged to the stable value. To improve the efficiency of sample processing, the integer-valued map indices of rotational samples are preserved and translated. All generated samples are analyzed to determine the maximum error direction. Then, a modified visual odometer is introduced for error compensation. The oriented fast and rotated brief (ORB) features are uniformly sampled in the image. A local map which contains key frames for reference is maintained. These two measures ensure that the modified visual odometer is able to return robust result which compensates the error of LIDAR-based pose tracking method in the maximum error direction.

Three experiments are conducted to prove the advantages of the proposed method. The proposed method can resist initial value disturbance with high computational efficiency, give back credible real-time result in the environment with abundant features and locate a robot in the environment with certain occlusion.

The proposed method is able to give back real-time pose tracking results with robustness. The iterative sample generation enables the robot to resist initial value disturbance. In each iteration, rotational and translational samples are separately generated to enhance computational efficiency. The maximum error direction of LIDAR-based pose tracking method is determined by principle component analysis and compensated by the result of modified visual odometer to give back correct pose in the environment with certain occlusion.

The purpose of this paper is to propose an enhanced pose tracking method using progressive scan matching, focusing on accuracy, time efficiency and robustness.

The general purpose of localization algorithms is to dynamically track a robot instead of globally locating one. In this paper, progressive scan matching is used to promote the performance of pose tracking. Rotational and translational samples are separately generated to accelerate the calculation and to increase the accuracy. Progressive iteration of sample generation can ensure localization to achieve a specific precision. The direction of localization uncertainty is taken into consideration to increase robustness. Nonlinear optimization is adopted to achieve a more precise result.

The proposed method was implemented on a self-made mobile robot. Two experiments were conducted to test the accuracy and time efficiency of the method. The comparison with the basic Monte Carlo localization shows the advantages of the method. Another two experiments were conducted to test the robustness of the method. The result shows that the method can relocate a robot from an inaccurate place if the offset is moderate.

An enhanced pose tracking method is proposed to promote the performance by separately processing rotational and translational samples, progressively iterating the sample generation, taking the direction of localization uncertainty into consideration and adopting nonlinear optimization. The proposed method enables a robot to accurately and quickly locate itself in the environment with robustness.