Lidar guided stereo simultaneous localization and mapping (SLAM) for UAV outdoor 3-D scene reconstruction

Gee, Trevor; James, Jason; Mark, W. van der; Delmas, Patrice; Gimel’farb, Georgy

doi:10.1109/ivcnz.2016.7804433

Cited by 30 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensors 2020, 20, 1890 3 of 21 In comparison, simultaneous localization and mapping (SLAM), which is one of the online-based methods, can successfully solve the AMP problem even when the environment is unknown [12][13][14][15]. Wang [12] presented a complete navigation system for an indoor UAV that was based on SLAM, and this system was able to ensure that the UAV could fly along the internal walls of a room without collisions.…”

Section: Related Workmentioning

confidence: 99%

Deep Reinforcement Learning Approach with Multiple Experience Pools for UAV’s Autonomous Motion Planning in Complex Unknown Environments

Wan

Gao

et al. 2020

Sensors

View full text Add to dashboard Cite

Autonomous motion planning (AMP) of unmanned aerial vehicles (UAVs) is aimed at enabling a UAV to safely fly to the target without human intervention. Recently, several emerging deep reinforcement learning (DRL) methods have been employed to address the AMP problem in some simplified environments, and these methods have yielded good results. This paper proposes a multiple experience pools (MEPs) framework leveraging human expert experiences for DRL to speed up the learning process. Based on the deep deterministic policy gradient (DDPG) algorithm, a MEP–DDPG algorithm was designed using model predictive control and simulated annealing to generate expert experiences. On applying this algorithm to a complex unknown simulation environment constructed based on the parameters of the real UAV, the training experiment results showed that the novel DRL algorithm resulted in a performance improvement exceeding 20% as compared with the state-of-the-art DDPG. The results of the experimental testing indicate that UAVs trained using MEP–DDPG can stably complete a variety of tasks in complex, unknown environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Reinforcement Learning Approach with Multiple Experience Pools for UAV’s Autonomous Motion Planning in Complex Unknown Environments

Wan

Gao

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…This method does not fully utilize the scene information of the LiDAR data map, but utilizes only that of the ground part; therefore, it has reduced robustness in special environments. A UAV platform is utilized to obtain prior LiDAR data and a stereo camera is used to map large-scale outdoor scenes without automatic initialization and real-time performance [41]. To address the real-time map optimization problem, a multithreaded segment-based map double window optimization strategy is adopted in the method proposed in this paper, to ensure consistency and accuracy of map construction, as well as high real-time performance.…”

Section: Related Workmentioning

confidence: 99%

Real-Time RGB-D Simultaneous Localization and Mapping Guided by Terrestrial LiDAR Point Cloud for Indoor 3-D Reconstruction and Camera Pose Estimation

Kang

Fan

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

In recent years, low-cost and lightweight RGB and depth (RGB-D) sensors, such as Microsoft Kinect, have made available rich image and depth data, making them very popular in the field of simultaneous localization and mapping (SLAM), which has been increasingly used in robotics, self-driving vehicles, and augmented reality. The RGB-D SLAM constructs 3D environmental models of natural landscapes while simultaneously estimating camera poses. However, in highly variable illumination and motion blur environments, long-distance tracking can result in large cumulative errors and scale shifts. To address this problem in actual applications, in this study, we propose a novel multithreaded RGB-D SLAM framework that incorporates a highly accurate prior terrestrial Light Detection and Ranging (LiDAR) point cloud, which can mitigate cumulative errors and improve the system’s robustness in large-scale and challenging scenarios. First, we employed deep learning to achieve system automatic initialization and motion recovery when tracking is lost. Next, we used terrestrial LiDAR point cloud to obtain prior data of the landscape, and then we applied the point-to-surface inductively coupled plasma (ICP) iterative algorithm to realize accurate camera pose control from the previously obtained LiDAR point cloud data, and finally expanded its control range in the local map construction. Furthermore, an innovative double window segment-based map optimization method is proposed to ensure consistency, better real-time performance, and high accuracy of map construction. The proposed method was tested for long-distance tracking and closed-loop in two different large indoor scenarios. The experimental results indicated that the standard deviation of the 3D map construction is 10 cm in a mapping distance of 100 m, compared with the LiDAR ground truth. Further, the relative cumulative error of the camera in closed-loop experiments is 0.09%, which is twice less than that of the typical SLAM algorithm (3.4%). Therefore, the proposed method was demonstrated to be more robust than the ORB-SLAM2 algorithm in complex indoor environments.

show abstract

“…Another kind of applicable approach is planning-based, which can address uncertain circumstances typically relying on a model of the environment [11−17]. If the environment model is available in advance, path (re-)planning [11−15] combined with trajectory following [16,17] can be used to realize an optimal controller that drives the UAV for flying across the envi-ronment autonomously. A series of specific approaches, such as A* algorithm [11], bio-inspired computation [12], dynamic planning [13,14], and artificial potential fields [15] have been used to generate optimal paths while facing a known environment.…”

Section: Introductionmentioning

confidence: 99%

A learning-based flexible autonomous motion control method for UAV in dynamic unknown environments

Wan

Gao

et al. 2021

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

This paper presents a deep reinforcement learning (DRL)-based motion control method to provide unmanned aerial vehicles (UAVs) with additional flexibility while flying across dynamic unknown environments autonomously. This method is applicable in both military and civilian fields such as penetration and rescue. The autonomous motion control problem is addressed through motion planning, action interpretation, trajectory tracking, and vehicle movement within the DRL framework. Novel DRL algorithms are presented by combining two difference-amplifying approaches with traditional DRL methods and are used for solving the motion planning problem. An improved Lyapunov guidance vector field (LGVF) method is used to handle the trajectory-tracking problem and provide guidance control commands for the UAV. In contrast to conventional motion-control approaches, the proposed methods directly map the sensorbased detections and measurements into control signals for the inner loop of the UAV, i.e., an end-to-end control. The training experiment results show that the novel DRL algorithms provide more than a 20% performance improvement over the state-ofthe-art DRL algorithms. The testing experiment results demonstrate that the controller based on the novel DRL and LGVF, which is only trained once in a static environment, enables the UAV to fly autonomously in various dynamic unknown environments. Thus, the proposed technique provides strong flexibility for the controller.

show abstract

Lidar guided stereo simultaneous localization and mapping (SLAM) for UAV outdoor 3-D scene reconstruction

Cited by 30 publications

References 23 publications

Deep Reinforcement Learning Approach with Multiple Experience Pools for UAV’s Autonomous Motion Planning in Complex Unknown Environments

Deep Reinforcement Learning Approach with Multiple Experience Pools for UAV’s Autonomous Motion Planning in Complex Unknown Environments

Real-Time RGB-D Simultaneous Localization and Mapping Guided by Terrestrial LiDAR Point Cloud for Indoor 3-D Reconstruction and Camera Pose Estimation

A learning-based flexible autonomous motion control method for UAV in dynamic unknown environments

Contact Info

Product

Resources

About