Learning-Based Methods of Perception and Navigation for Ground Vehicles in Unstructured Environments: A Review

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.

An Optimization-Based Motion Planner for Car-like Logistics Robots on Narrow Roads

Thanks to their strong maneuverability and high load capacity, car-like robots with non-holonomic constraints are often used in logistics to improve efficiency. However, it is difficult to plan a safe and smooth optimal path in real time on the restricted narrow roads of the logistics park. To solve this problem, an optimization-based motion planning method inspired by the Timed-Elastic-Band algorithm is proposed, called Narrow-Roads-Timed-Elastic-Band (NRTEB). Three optimization modules are added to the inner and outer workflow of the Timed-Elastic-Band framework. The simulation results show that the proposed method achieves safe reversing planning on narrow roads while the jerk of the trajectory is reduced by 72.11% compared to the original method. Real-world experiments reveal that the proposed method safely and smoothly avoids dynamic obstacles in real time when navigating forward and backward. The motion planner provides a safer and smoother trajectory for car-like robots on narrow roads in real time, which greatly enhances the safety, robustness and reliability of the Timed-Elastic-Band planner in logistics parks.

Off-Road Detection Analysis for Autonomous Ground Vehicles: A Review

When it comes to some essential abilities of autonomous ground vehicles (AGV), detection is one of them. In order to safely navigate through any known or unknown environment, AGV must be able to detect important elements on the path. Detection is applicable both on-road and off-road, but they are much different in each environment. The key elements of any environment that AGV must identify are the drivable pathway and whether there are any obstacles around it. Many works have been published focusing on different detection components in various ways. In this paper, a survey of the most recent advancements in AGV detection methods that are intended specifically for the off-road environment has been presented. For this, we divided the literature into three major groups: drivable ground and positive and negative obstacles. Each detection portion has been further divided into multiple categories based on the technology used, for example, single sensor-based, multiple sensor-based, and how the data has been analyzed. Furthermore, it has added critical findings in detection technology, challenges associated with detection and off-road environment, and possible future directions. Authors believe this work will help the reader in finding literature who are doing similar works.

Application of Smoothing Spline in Determining the Unmanned Ground Vehicles Route Based on Ultra-Wideband Distance Measurements

Unmanned ground vehicles (UGVs) are technically complex machines to operate in difficult or dangerous environmental conditions. In recent years, there has been an increase in research on so called "following vehicles". The said concept introduces a guide-an object that sets the route the platform should follow. Afterwards, the role of the UGV is to reproduce the mentioned path. The article is based on the field test results of an outdoor localization subsystem using ultra-wideband technology. It focuses on determining the guide's route using a smoothing spline for constructing a UGV's path planning subsystem, which is one of the stages for implementing a "follow-me" system. It has been shown that the use of a smoothing spline, due to the implemented mathematical model, allows for recreating the guide's path in the event of data decay lasting up to a several seconds. The innovation of this article originates from influencing studies on the smoothing parameter of the estimation errors of the guide's location.

Autonomous robotic exploration with simultaneous environment and traversability models learning

In this study, we address generalized autonomous mobile robot exploration of unknown environments where a robotic agent learns a traversability model and builds a spatial model of the environment. The agent can benefit from the model learned online in distinguishing what terrains are easy to traverse and which should be avoided. The proposed solution enables the learning of multiple traversability models, each associated with a particular locomotion gait, a walking pattern of a multi-legged walking robot. We propose to address the simultaneous learning of the environment and traversability models by a decoupled approach. Thus, navigation waypoints are generated using the current spatial and traversability models to gain the information necessary to improve the particular model during the robot's motion in the environment. From the set of possible waypoints, the decision on where to navigate next is made based on the solution of the generalized traveling salesman problem that allows taking into account a planning horizon longer than a single myopic decision. The proposed approach has been verified in simulated scenarios and experimental deployments with a real hexapod walking robot with two locomotion gaits, suitable for different terrains. Based on the achieved results, the proposed method exploits the online learned traversability models and further supports the selection of the most appropriate locomotion gait for the particular terrain types.

Automatically Annotated Dataset of a Ground Mobile Robot in Natural Environments via Gazebo Simulations

This paper presents a new synthetic dataset obtained from Gazebo simulations of an Unmanned Ground Vehicle (UGV) moving on different natural environments. To this end, a Husky mobile robot equipped with a tridimensional (3D) Light Detection and Ranging (LiDAR) sensor, a stereo camera, a Global Navigation Satellite System (GNSS) receiver, an Inertial Measurement Unit (IMU) and wheel tachometers has followed several paths using the Robot Operating System (ROS). Both points from LiDAR scans and pixels from camera images, have been automatically labeled into their corresponding object class. For this purpose, unique reflectivity values and flat colors have been assigned to each object present in the modeled environments. As a result, a public dataset, which also includes 3D pose ground-truth, is provided as ROS bag files and as human-readable data. Potential applications include supervised learning and benchmarking for UGV navigation on natural environments. Moreover, to allow researchers to easily modify the dataset or to directly use the simulations, the required code has also been released.

Adaptive Articulation Angle Preview-Based Path-Following Algorithm for Tractor-Semitrailer Using Optimal Control

Most existing Path-Following Algorithms (PFAs) are developed for single-unit vehicles (SUVs) and rarely for articulated vehicles (AVs). Since these PFAs ignore the motion of the trailer, they may cause large tracking deviations and ride stability issues when cornering. To this end, an Adaptive Articulation Angle Preview-based Path-Following Algorithm (AAAP-PFA) is proposed for AVs. Different from previous PFAs, in this model, a simple linear vehicle dynamics model is used as the prediction model, and an offset distance calculated by an articulation angle is used as part of the preview distance. An adaptive posture control strategy is designed to trade off the trajectory tracking performance and lateral stability performance during the path-following process. Considering a large prediction mismatch caused by using a linear vehicle dynamics model, a feedback correction method is proposed to improve the robustness of the steering control. In the comparison simulation experiment with SUV-PFA, it is confirmed that the novel PFA has better adaptability to the contradictory relationship between tracking performance and lateral stability and has strong steering control robustness.

SLAM, Path Planning Algorithm and Application Research of an Indoor Substation Wheeled Robot Navigation System

Staff safety is not assured due to the indoor substation’s high environmental risk factor. The Chinese State Grid Corporation has been engaged in the intelligentization of substations and the employment of robots for inspection tasks. The autonomous navigation and positioning system of the mobile chassis is the most important feature of this type of robot, as it allows the robot to perceive the surrounding environment information at the initial position using its own sensors and find a suitable path to move to the target point to complete the task. Automatic navigation is the basis for the intelligentization of indoor substation robots, which is of great significance to the efficient and safe inspection of indoor substations. Based on this, this paper formulates a new navigation system, and builds a chassis simulation environment in the Robot Operating System (ROS). To begin with, we develop a novel hardware and sensor-based chassis navigation system experimental platform. Secondly, to conduct the fusion of the odometer and inertial navigation data, the Extended Kalman Filter (EKF) is used. The map’s creation approach determines how the environmental map is created. The global path is scheduled with the A* algorithm, whereas the local path is scheduled with the Dynamic Window Method (DWA). Finally, the created robot navigation system is applied to an auxiliary operation robot chassis suited for power distribution cabinet switch and the navigation system’s experimental analysis is conducted using this platform, demonstrating the system’s efficacy and practicability.

The Intelligent Path Planning System of Agricultural Robot via Reinforcement Learning

Agricultural robots are one of the important means to promote agricultural modernization and improve agricultural efficiency. With the development of artificial intelligence technology and the maturity of Internet of Things (IoT) technology, people put forward higher requirements for the intelligence of robots. Agricultural robots must have intelligent control functions in agricultural scenarios and be able to autonomously decide paths to complete agricultural tasks. In response to this requirement, this paper proposes a Residual-like Soft Actor Critic (R-SAC) algorithm for agricultural scenarios to realize safe obstacle avoidance and intelligent path planning of robots. In addition, in order to alleviate the time-consuming problem of exploration process of reinforcement learning, this paper proposes an offline expert experience pre-training method, which improves the training efficiency of reinforcement learning. Moreover, this paper optimizes the reward mechanism of the algorithm by using multi-step TD-error, which solves the probable dilemma during training. Experiments verify that our proposed method has stable performance in both static and dynamic obstacle environments, and is superior to other reinforcement learning algorithms. It is a stable and efficient path planning method and has visible application potential in agricultural robots.

Navigation Map-Based Artificial Intelligence

A biologically inspired cognitive architecture is described which uses navigation maps (i.e., spatial locations of objects) as its main data elements. The navigation maps are also used to represent higher-level concepts as well as to direct operations to perform on other navigation maps. Incoming sensory information is mapped to local sensory navigation maps which then are in turn matched with the closest multisensory maps, and then mapped onto a best-matched multisensory navigation map. Enhancements of the biologically inspired feedback pathways allow the intermediate results of operations performed on the best-matched multisensory navigation map to be fed back, temporarily stored, and re-processed in the next cognitive cycle. This allows the exploration and generation of cause-and-effect behavior. In the re-processing of these intermediate results, navigation maps can, by core analogical mechanisms, lead to other navigation maps which offer an improved solution to many routine problems the architecture is exposed to. Given that the architecture is brain-inspired, analogical processing may also form a key mechanism in the human brain, consistent with psychological evidence. Similarly, for conventional artificial intelligence systems, analogical processing as a core mechanism may possibly allow enhanced performance.

An autonomous navigation approach for unmanned vehicle in outdoor unstructured terrain with dynamic and negative obstacles

At present, the study on autonomous unmanned ground vehicle navigation in an unstructured environment is still facing great challenges and is of great significance in scenarios where search and rescue robots, planetary exploration robots, and agricultural robots are needed. In this paper, we proposed an autonomous navigation method for unstructured environments based on terrain constraints. Efficient path search and trajectory optimization on octree map are proposed to generate trajectories, which can effectively avoid various obstacles in off-road environments, such as dynamic obstacles and negative obstacles, to reach the specified destination. We have conducted empirical experiments in both simulated and real environments, and the results show that our approach achieved superior performance in dynamic obstacle avoidance tasks and mapless navigation tasks compared to the traditional 2-dimensional or 2.5-dimensional navigation methods.

Dual-Rate Extended Kalman Filter Based Path-Following Motion Control for an Unmanned Ground Vehicle: Realistic Simulation

In this paper, a two-wheel drive unmanned ground vehicle (UGV) path-following motion control is proposed. The UGV is equipped with encoders to sense angular velocities and a beacon system which provides position and orientation data. Whereas velocities can be sampled at a fast rate, position and orientation can only be sensed at a slower rate. Designing a dynamic controller at this slower rate implies not reaching the desired control requirements, and hence, the UGV is not able to follow the predefined path. The use of dual-rate extended Kalman filtering techniques enables the estimation of the fast-rate non-available position and orientation measurements. As a result, a fast-rate dynamic controller can be designed, which is provided with the fast-rate estimates to generate the control signal. The fast-rate controller is able to achieve a satisfactory path following, outperforming the slow-rate counterpart. Additionally, the dual-rate extended Kalman filter (DREKF) is fit for dealing with non-linear dynamics of the vehicle and possible Gaussian-like modeling and measurement uncertainties. A Simscape Multibody™ (Matlab^®/Simulink) model has been developed for a realistic simulation, considering the contact forces between the wheels and the ground, not included in the kinematic and dynamic UGV representation. Non-linear behavior of the motors and limited resolution of the encoders have also been included in the model for a more accurate simulation of the real vehicle. The simulation model has been experimentally validated from the real process. Simulation results reveal the benefits of the control solution.