A Hybrid Technique for Active SLAM Based on RPPO Model with Transfer Learning

The problem of exploration in unknown environments is still a great challenge for autonomous mobile robots due to the lack of a priori knowledge. Active Simultaneous Localization and Mapping (SLAM) is an effective method to realize obstacle avoidance and autonomous navigation. Traditional Active SLAM is usually complex to model and difficult to adapt automatically to new operating areas. This paper presents a novel Active SLAM algorithm based on Deep Reinforcement Learning (DRL). The Relational Proximal Policy Optimization (RPPO) model with deep separable convolution and data batch processing is used to predict the action strategy and generate the action plan through the acquired environment RGB images, so as to realize the autonomous collision free exploration of the environment. Meanwhile, Gmapping is applied to locate and map the environment. Then, based on Transfer Learning, Active SLAM algorithm is applied to complex unknown environments with various dynamic and static obstacles. Finally, we present several experiments to demonstrate the advantages and feasibility of the proposed Active SLAM algorithm.

Occupancy grid mapping for rover navigation based on semantic segmentation

Obstacle mapping is a fundamental building block of the autonomous navigation pipeline of many robotic platforms such as planetary rovers. Nowadays, occupancy grid mapping is a widely used tool for obstacle perception. It foreseen the representation of the environment in evenly spaced cells, whose posterior probability of being occupied is updated based on range sensors measurement. In more classic approaches, the cells are updated to occupied at the point where the ray emitted by the range sensor encounters an obstacle, such as a wall. The main limitation of this kind of methods is that they are not able to identify planar obstacles, such as slippery, sandy, or rocky soils. In this work, we use the measurements of a stereo camera combined with a pixel labeling technique based on Convolution Neural Networks to identify the presence of rocky obstacles in planetary environment. Once identified, the obstacles are converted into a scan-like model. The estimation of the relative pose between successive frames is carried out using ORB-SLAM algorithm. The final step consists of updating the occupancy grid map using the Bayes’ update Rule. To evaluate the metrological performances of the proposed method images from the Martian analogous dataset, the ESA Katwijk Beach Planetary Rover Dataset have been used. The evaluation has been performed by comparing the generated occupancy map with a manually segmented ortomosaic map, obtained by drones’ survey of the area used as reference.

Visual Simultaneous Localization and Mapping (vSLAM) of Driverless Car in GPS-Denied Areas

A simultaneous localization and mapping (SLAM) algorithm allows a mobile robot or a driverless car to determine its location in an unknown and dynamic environment where it is placed, and simultaneously allows it to build a consistent map of that environment. Driverless cars are becoming an emerging reality from science fiction, but there is still too much required for the development of technological breakthroughs for their control, guidance, safety, and health related issues. One existing problem which is required to be addressed is SLAM of driverless car in GPS denied-areas, i.e., congested urban areas with large buildings where GPS signals are weak as a result of congested infrastructure. Due to poor reception of GPS signals in these areas, there is an immense need to localize and route driverless car using onboard sensory modalities, e.g., LIDAR, RADAR, etc., without being dependent on GPS information for its navigation and control. The driverless car SLAM using LIDAR and RADAR involves costly sensors, which appears to be a limitation of this approach. To overcome these limitations, in this article we propose a visual information-based SLAM (vSLAM) algorithm for GPS-denied areas using a cheap video camera. As a front-end process, features-based monocular visual odometry (VO) on grayscale input image frames is performed. Random Sample Consensus (RANSAC) refinement and global pose estimation is performed as a back-end process. The results obtained from the proposed approach demonstrate 95% accuracy with a maximum mean error of 4.98.

Improving RGB-D SLAM in dynamic environments using semantic aided segmentation

Summary Most conventional simultaneous localization and mapping (SLAM) approaches assume the working environment to be static. In a highly dynamic environment, this assumption divulges the impediments of a SLAM algorithm that lack modules that distinctively attend to dynamic objects despite the inclusion of optimization techniques. This work exploits such environments and reduces the effects of dynamic objects in a SLAM algorithm by separating features belonging to dynamic objects and static background using a generated binary mask image. While the features belonging to the static region are used for performing SLAM, the features belonging to non-static segments are reused instead of being eliminated. The approach employs deep neural network or DNN-based object detection module to obtain bounding boxes and then generates a lower resolution binary mask image using depth-first search algorithm over the detected semantics, characterizing the segmentation of the foreground from the static background. In addition, the features belonging to dynamic objects are tracked into consecutive frames to obtain better masking consistency. The proposed approach is tested on both publicly available dataset as well as self-collected dataset, which includes both indoor and outdoor environments. The experimental results show that the removal of features belonging to dynamic objects for a SLAM algorithm can significantly improve the overall output in a dynamic scene.

Improved UKF-SLAM with Lie Group Operation and Robust Feature Tracking for Motion Vehicles

This paper proposes an improved simultaneous localization and mapping (SLAM) algorithm based on tightly coupled camera images and IMU data, which provides accurate and robust localization for autonomous vehicles and unmanned aerial vehicles (UAV), especially for those in GPS-denied environments. Many research efforts have demonstrated the effectiveness of fusing camera images and inertial data with the Unscented Kalman filter (UKF), but there is still one tricky problem about the non-linearity of the kinematics of rotations. To address this issue, we propose a novel UKF-SLAM approach by rebuilding system and measurement models based on the Lie group and Lie algebra, which obtains state estimates with reasonably high accuracy. Besides, we also offer a new method to handle corner matching outliers, which only causes slightly additional computation costs but eliminates outliers and enhances corner tracking robustness. Results from extensive experimental data have validated the effectiveness of the proposed approach, and this method also achieves comparable precision to the state-of-art.

Visual odometry in local underwater navigation problems

The work processes of the ORB-SLAM algorithm are presented. The results of experimental studies on temporal comparisons of the operation of the algorithm with different parameters and cameras are presented. The necessity of forming a visual odometry (VO) system as a local navigation of remote-controlled and autonomous underwater robots has been substantiated. The two most suitable odometry methods in the underwater environment are described, such as their advantages and disadvantages. The work processes of the ORB-SLAM algorithm are presented. The results of experimental studies on temporal comparisons of the operation of the algorithm with different parameters and cameras are presented. The procedure for preparing video data is described: processing a video stream, adjusting camera parameters for calibration. The experiments represent the testing of the ORB-SLAM3 algorithm on a sample of video filmed as part of the ecological monitoring of the Caspian shelf in 2020.