Coupled Sensor Configuration and Path-Planning in Unknown Environments with Adaptive Cluster Analysis

Robot path planning in complex and unknown environment is a challenging task. To deal with this problem, an improved PSO method based on bio-inspired neural network is proposed, where a bio-inspired neural network is used to optimize the fitness function of the PSO based method. A dynamic environment modeling method is introduced to realize the path planning in unknown environment. Finally, some simulation experiments on various environments are conducted. The results show the efficiency of the proposed method.

Path planning in unknown environments is one of the most challenging research areas in robotics. In this class of path planning, the robot acquires the information from its sensory system. Sampling-based path planning is one of the famous approaches with low memory and computational requirements that has been studied by many researchers during the past few decades. We propose a sampling-based algorithm for path planning in unknown environments using Tabu search. The Tabu search component of our method guides the sampling to find the samples in the most promising areas and makes the sampling procedure more intelligent. The simulation results show the efficient performance of the proposed approach in different types of environments. We also compare the performance of the algorithm with some of the well-known path planning approaches, including Bug1, Bug2, SRT, potential fields and the visibility graph. Furthermore, two different sampling strategies were used in the sampling procedure, including uniform and Gaussian distributions.

The ability of a robot to find a goal in an unknown environment is significantly improved from previous path planners with the synthesis of intelligence and reflexive algorithms as a path planning approach. A hybrid expert system vector field (HESV) path planner is introduced and tested in 100 map scenarios using a custom robotic simulation shell. The method combines a trap detection expert system, a low-level reflexive obstacle avoidance algorithm, and a trap evasion expert system, to achieve improved performance without sacrificing computational efficiency. Simulation results and evaluations are presented for the potential field, vector field, and HESV techniques. HESV's expert systems have been simplified to illustrate the performance improvements that result from a small amount of intelligence. Although recommendations for the structure of the path planning system are given, the purpose of the paper is to show the effectiveness of intelligent rules in path planning, rather than to define the actual rules to be used.

An important challenge for air–ground unmanned systems achieving autonomy is navigation, which is essential for them to accomplish various tasks in unknown environments. This paper proposes an end-to-end framework for solving air–ground unmanned system navigation using deep reinforcement learning (DRL) while optimizing by using a priori information from search-based path planning methods, which we call search-based optimizing DRL (SO-DRL) for the air–ground unmanned system. SO-DRL enables agents, i.e., an unmanned aerial vehicle (UAV) or an unmanned ground vehicle (UGV) to move to a given target in a completely unknown environment using only Lidar, without additional mapping or global planning. Our framework is equipped with Deep Deterministic Policy Gradient (DDPG), an actor–critic-based reinforcement learning algorithm, to input the agents’ state and laser scan measurements into the network and map them to continuous motion control. SO-DRL draws on current excellent search-based algorithms to demonstrate path planning and calculate rewards for its behavior. The demonstrated strategies are replayed in an experienced pool along with the autonomously trained strategies according to their priority. We use a multi-stage training approach based on course learning to train SO-DRL on the 3D simulator Gazebo and verify the robustness and success of the algorithm using new test environments for path planning in unknown environments. The experimental results show that SO-DRL can achieve faster algorithm convergence and a higher success rate. We piggybacked SO-DRL directly onto a real air–ground unmanned system, and SO-DRL can guide a UAV or UGV for navigation without adjusting any networks.

This paper proposes a new method, minimum risk approach, to address the local path planning to escape from local minimum during goal-oriented robot navigation in unknown environments. This approach is theoretically proved to guarantee global convergence even in the long-wall, unstructured, cluttered, maze-like, and modified environments. The approach adopts a strategy of multi-behavior coordination, in which a novel path-searching behavior is developed to recommend the regional direction with minimum risk. The paper provides a fuzzy logic framework to implement the behavior design and coordination. It is verified by the simulated and real world tests.

The artificial potential field algorithm has been widely applied to mobile robots and robotic arms due to its advantage of enabling simple and efficient path planning in unknown environments. However, solving the local minimum problem is an essential task and is still being studied. Among current methods, the technique using the virtual hill concept is reliable and suitable for real-time path planning because it does not create a new local minimum and provides lower complexity. However, in the previous study, the shape of the obstacles was not considered in determining the robot’s direction at the moment it is trapped in a local minimum. For this reason, longer or blocked paths are sometimes selected. In this study, we propose an enhanced virtual hill algorithm to reduce errors in selecting the driving direction and improve the efficiency of robot movement. In the local minimum area, a dead-end algorithm is also proposed that allows the robot to return without entering deeply when it encounters a dead end.

Path planning in unknown environments has been a major challenge for robots. With the recent development of artificial intelligence, deep reinforcement learning has been gradually used to study the path-planning problem of robots in unknown environments due to its autonomous learning characteristics. However, deep reinforcement learning can produce a large amount of redundant data during model training, which reduces the training efficiency. To address this problem, this study proposes a path-planning algorithm based on deep reinforcement learning with a dual-experience pool playback structure. The proposed method realises the segmentation of data using two experience pools and simultaneously adjusts the ratio of experience playback to improve the speed of model training. The proposed algorithm is validated by experiments on a simulation platform using a Turtlebot3 robot. The experimental results show that the proposed algorithm performs better than the commonly used DQN and Double DQN algorithms in terms of convergence speed and accuracy.

An autonomous mobile robot needs to many tasks such as a self-localization, collision detection, and path planning to a target position in an unknown environment. Therefore, it is important for the robot to build environmental maps with different resolutions in each work space. In addition, the robot requires the path planning capability in the unknown environment for applying the robot to various environment such as a disaster site and commercial construction. This research proposes a Growing Neural Gas based topological environmental map building method from a metric map with high resolution map for using the self-localization. Our proposed method enables to build the topological map with occupancy information of the metric map and preserve the geometric feature of the map simultaneously. Next, the path planning method in the unknown environment is proposed by utilizing the occupancy information of the topological map. Finally, we conduct on several experiments for evaluating our proposed method by comparing to other conventional approaches, and discuss the effectiveness of our proposed method.

13 - Experimental Studies

In recent years, most of the research about autonomous mobile robotics is focused on obstacle detection and path planning in unknown environments. Improved accuracy in environment recognition and high precision in robot control can ensure feasibility of intelligent and autonomous mobile robotic systems in unexplored environments. To reach this goal, effective navigation and control approaches for the mobile robots must be proposed. This paper presents a path planning approach based on the navigation map reconstructed by a scout robot equipped with an onboard camera using VSLAM (visual simultaneous localization and mapping) algorithm. In the region where surveillance cameras can see blind robots equipped with no onboard cameras, these blind robots can be driven to follow the desired trajectories and reach their goal positions by the proposed visual servo control law. The proposed navigation and control system has been validated by experimenting with a blind robot using available real-time vision from the surveillance cameras.

Aiming at the path planning for coal mine detection robot in unknown static environment, a path planning method is propounded which couples behavioural dynamics with rolling scan information. Firstly, the method of sub-target's choice is provided using heuristic function according to the rolling scan information L it is local environment information L which is obtained by sensors. Then path planning is divided into trending to target behaviour and obstacle avoidance behaviour L their behaviour state and behaviour pattern dynamics modes are established L and then one autonomous local path planning technology is implemented using behaviour dynamics mode in a single rolling scan region. Connecting a series of local paths tandem according to continuity, the global path planning is accomplished ultimately. The method has a simple principle and low calculating burden L smooth path and high applied value. The method's efficiency and adaptability is verified by simulation experiment. (5 pages)

A new complete coverage path planning algorithm based on rolling path planning, dynamic heuristic searching and directly filling is proposed to improve efficiency of path planning for mobile robot in unknown environments. The biological inspired neural network was used to model the environment of mobile robot. After the characteristic of local environment around robot was identified on line, the dynamic heuristic planning method combing static searching and following the boundary of obstacle is applied and generated path is much shorter and less turning. Using virtual obstacle and directly filling algorithm, the continuously covered area in U shape obstacle is obtained in unknown environments. The effectiveness of the proposed algorithm is validated by simulation in unknown complicated environments.

This paper describes an adaptive robot speed control method for safe and efficient navigation in unknown environments. Speed control is important in the following two cases. (1) When a robot moves enters a narrow free space, it needs to control the speed to avoid any collision considering the motion uncertainty. (2) When a robot enters a region whose vacancy (i.e., being free) has not been decided yet, it needs to control the speed so that it can observe the region sufficiently to be confident with the vacancy of the region. This paper proposes a simple but effective strategy for speed control that the robot selects the fastest safe speed. To adopt this strategy, we define criteria for judging a speed is safe for the above two cases. The proposed method successfully made the robot move around in unknown static environments with adaptively controlling the speed.

Local or sensor-based path planning in an unknown environment is a challenging problem for mobile robots. In completely known grid environments, the shortest Euclidean-length path connecting a given start-goal point pair can be generated using the Fast Marching Method (FMM). In contrast, in unknown environments, path planning must be reactive (i.e. based on recent sensory information) and boundary following (BF) is one type of reactive path planning technique. In [1], a hybrid method called Boundary Following FMM (BFFMM) was proposed that could extend the applicability of FMM to work well in an unknown environment using only local sensory perceptions. Bug algorithms are one family of navigation algorithms that also utilize BF technique in planning paths in unknown environments. This paper compares the path length of the paths generated by BFFMM with those by Bug1 and Bug2, the earliest versions of the Bug family algorithms to quantitatively reveal the effects of environment uncertainties on length of paths generated by navigation methods using boundary following. By comparison, BFFMM is a modest mobile robot path planner that bridges the gap between unknown and known terrain.

Unmanned vehicles in urban structured environments have become the main battlefields of related companies all over the world. By relying on high-precision maps established in advance, unmanned vehicles can perform well enough. However, this method is difficult to apply to unknown off-road environment which cannot obtain high-precision maps in advance, such as transportation and target search of dangerous scenes in the wild. In this paper, we introduce a novel and efficient real-time path planning method for autonomous driving in unknown environments with sparse waypoints. The contributions of this paper are as follows. First, we present a goal point extraction algorithm to extract the goal configuration in free space for local path planning. It is extremely suitable for the sparse waypoints situation, in which local perception map may not contain any waypoints. Second, we present a novel path re-planning algorithm for large-scale environment without SLAM(Simultaneous Localization And Mapping) by building a topology map constantly. Our method not only overcame the failure of path planning due to the limited on-board sensing range, but also avoided high computing resource consumption brought by the large-scale construction maintenance of SLAM. A large number of challenging real off-road scenarios show that the proposed method can effectively solve the problem that unmanned vehicles cannot plan to travel due to sparse waypoints, and give real-time effective planning results when unmanned vehicles need to carry out large-scale path re-planning.