Obstacle Avoidance Strategy Research Articles

An obstacle avoidance strategy for the wave glider based on the improved artificial potential field and collision prediction model

Wave glider, as a wave-propelled and persistent unmanned surface vehicle, has attracted wide attention in recent years. Due to its long voyage, the wave glider inevitably encounters various obstacles at sea, which may cause collision accidents. However, the obstacle avoidance for wave glider is challenging because of its special two-body structure and motion mechanism. In this paper, the obstacle avoidance research of wave glider in marine environment is conducted. To address the local minimum in the traditional artificial potential field, an improved artificial potential field (IAPF) is proposed. An eight-degree-of-freedom mathematical model of the wave glider is presented, and the model in series with IAPF is verified under static obstacle environment. Aiming at the obstacle avoidance under dynamic obstacle environment, a fusion algorithm based on the collision prediction model (CPM) and IAPF (CPM-IAPF) is proposed. The algorithm can overcome the obstacle avoidance difficulties caused by the weak maneuverability of wave glider. Various simulations are performed to demonstrate the feasibility and robustness of the proposed strategy. The simulation results show that the wave glider can accomplish the obstacle avoidance task with the proposed CPM-IAPF algorithm when facing with different dynamic obstacles under various marine environments.

Socially-Aware Reactive Obstacle Avoidance Strategy Based on Limit Cycle

The letter proposes a combination of ideas to support navigation for a mobile robot across dynamic environments, cluttered with obstacles and populated by human beings. The combination of the classical potential field methods and limit cycle based approach with an innovative shape for the limit cycles, generates paths which are reasonably short, smooth and comfortable to follow (which can be very important for assistive robots), and it respects the safety and psychological comfort of the bystanders by staying clear of their private space.

How perception of personal space influence obstacle avoidance during walking: differences between young and older adults.

Individuals maintain a spatial margin or 'personal space' between themselves and others. The form of this space and strategies for avoiding obstacles can be influenced by participant characteristics such as age. In this study, we investigated the characteristics of personal space and obstacle avoidance strategies in young and older adults. We also examined differences in perceptual personal space and walking trajectory during obstacle avoidance using a three-dimensional motion capture system. Methods Ten young adults and ten older adults participated in this study. We calculated actual obstacle avoidance trajectory and obstacle avoidance data such as the lateral spatial margin and body rotation angle during walking in a task that included obstacle avoidance. We also measured the perceptual personal space created by approaching a confederate. In order to calculate each personal space and obstacle avoidance data, we used a three-dimensional motion capture system. Two factors (two groups and personal space) of repeated analysis of variance were used in statistical analysis. Results We found no age-related differences in personal space or obstacle avoidance strategy in this study (F = 0.52, p = 0.48). However, we found significant differences in the form of perceptual personal space and personal space formed during obstacle avoidance (F = 11.86, p = 0.0030). Conclusion This study indicates that perceptual personal space did not reflect the walking trajectory created by actual obstacle avoidance. In addition, age did not influence the obstacle avoidance strategy. These results suggest that the perceptual personal space and aging have little effect in the situation of avoiding a single standing pedestrian.

A hybrid legged-wheeled obstacle avoidance strategy for service operations

Hybrid legged-wheeled robots are gaining interest in various service applications, like surveillance or inspection in hospitals. The autonomy of these robots is not only related to their power consumption, it mostly refers to their capability to safely move in complex partially structured environments. This paper proposes to investigate the combination of different moving strategies and sensors to enhance the adaptability and autonomy of a hybrid hexapod robot in specific environments shared with humans. Namely, this paper proposes a locomotion strategy that combines leg motions and Mecanum omniwheels with multiple sensory feedbacks to achieve safe obstacle avoidance during a service operation. Several experimental tests are carried out by using Cassino Hexapod III in combination with sonar, IMU and Lidar sensors at IRCCS Neuromed site in Pozzilli. Experimental results show the effectiveness of the proposed operation strategy with Cassino Hexapod III to avoid multiple obstacles.

Navigation of Semi-autonomous Service Robots Using Local Information and Anytime Motion Planners

SUMMARYThis paper deals with the problem of navigating semi-autonomous mobile robots without global localization systems in unknown environments. We propose a planning-based obstacle avoidance strategy that relies on local maps and a series of short-time coordinate frames. With this approach, simple odometry and range information are sufficient to make the robot to safely follow the user commands. Different from reactive obstacle avoidance strategies, the proposed approach chooses a good and smooth local path for the robot. The methodology is evaluated using a mobile service robot moving in an unknown corridor environment populated with obstacles and people.

Avoidance of non-localizable obstacles in echolocating bats: A robotic model.

Most objects and vegetation making up the habitats of echolocating bats return a multitude of overlapping echoes. Recent evidence suggests that the limited temporal and spatial resolution of bio-sonar prevents bats from separately perceiving the objects giving rise to these overlapping echoes. Therefore, bats often operate under conditions where their ability to localize obstacles is severely limited. Nevertheless, bats excel at avoiding complex obstacles. In this paper, we present a robotic model of bat obstacle avoidance using interaural level differences and distance to the nearest obstacle as the minimal set of cues. In contrast to previous robotic models of bats, the current robot does not attempt to localize obstacles. We evaluate two obstacle avoidance strategies. First, the Fixed Head Strategy keeps the acoustic gaze direction aligned with the direction of flight. Second, the Delayed Linear Adaptive Law (DLAL) Strategy uses acoustic gaze scanning, as observed in hunting bats. Acoustic gaze scanning has been suggested to aid the bat in hunting for prey. Here, we evaluate its adaptive value for obstacle avoidance when obstacles can not be localized. The robot's obstacle avoidance performance is assessed in two environments mimicking (highly cluttered) experimental setups commonly used in behavioral experiments: a rectangular arena containing multiple complex cylindrical reflecting surfaces and a corridor lined with complex reflecting surfaces. The results indicate that distance to the nearest object and interaural level differences allows steering the robot clear of obstacles in environments that return non-localizable echoes. Furthermore, we found that using acoustic gaze scanning reduced performance, suggesting that gaze scanning might not be beneficial under conditions where the animal has limited access to angular information, which is in line with behavioral evidence.

Fuzzy obstacle avoidance optimization of soccer robot based on an improved genetic algorithm

Due to its high-tech confrontation and entertainment, soccer robots have attracted a large number of researchers to participate in it. Robot obstacle avoidance is an active research branch in the field of intelligent robot technology, and is a comprehensive subject covering multiple disciplines. The traditional obstacle avoidance method of soccer robots has the disadvantages of poor local optimization ability and slow convergence speed, and it is easy to fall into local extreme points. Based on the active obstacle avoidance strategy of local sensors and processors, this paper studies the method of automatic extraction and optimization of fuzzy rules of fuzzy path planner by genetic algorithm. This fuzzy control method does not depend on accurate environmental information, and has a small amount of computation and learning ability. A fitness function for evaluating the validity of a rule is proposed. The simulation results show that the algorithm has good applicability.

Stepping over multiple obstacles changes the pattern of foot integrated pressure of the leading and trailing legs

An efficient obstacle avoidance strategy when stepping over a single obstacle was reported in the literature – the total impulse of the leading and of the trailing legs are equal even though the kinematics parameters of two legs are different. However, does this efficient obstacle avoidance strategy exist when stepping over multiple obstacles? The study attempted to answer this question. Nineteen healthy young adults (25.84 ± 3.35 years) were recruited and performed multiple obstacle crossings when intervals between two obstacles were one-step, two-step, and three-step away, respectively. The dependent variables were foot integrated pressure (FIP) and other kinematic parameters – horizontal distance (HD, a heel-contact-to-obstacle distance of the leading leg/toe-off-to-obstacle distance of the trailing leg) and vertical distance (VD, toe clearance of both legs). A significant interaction among the effect of different legs, different intervals, and different obstacles on FIP, and kinematic parameters of HD and VD was found (p < 0.0001, p = 0.001, p < 0.001). Also, when the obstacle intervals were two-step and three-step away, the FIPs of the leading leg were significantly greater when stepping over the second obstacle than when stepping over the first one (p < 0.05, p < 0.01, respectively). These significantly greater FIPs might be attributed to the shorter HD (p < 0.001, p < 0.001) of the trailing leg, and the longer HD (p < 0.001, p < 0.001) of the leading leg. These results suggested that there is an inefficient obstacle avoidance pattern when stepping over the second obstacle.

Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance Targeting Neuromorphic Processors

The Lobula giant movement detector (LGMD) is an identified neuron of the locust that detects looming objects and triggers the insect's escape responses. Understanding the neural principles and network structure that leads to these fast and robust responses can facilitate the design of efficient obstacle avoidance strategies for robotic applications. Here, we present a neuromorphic spiking neural network model of the LGMD driven by the output of a neuromorphic dynamic vision sensor (DVS), which incorporates spiking frequency adaptation and synaptic plasticity mechanisms, and which can be mapped onto existing neuromorphic processor chips. However, as the model has a wide range of parameters and the mixed-signal analog-digital circuits used to implement the model are affected by variability and noise, it is necessary to optimize the parameters to produce robust and reliable responses. Here, we propose to use differential evolution (DE) and Bayesian optimization (BO) techniques to optimize the parameter space and investigate the use of self-adaptive DE (SADE) to ameliorate the difficulties of finding appropriate input parameters for the DE technique. We quantify the performance of the methods proposed with a comprehensive comparison of different optimizers applied to the model and demonstrate the validity of the approach proposed using recordings made from a DVS sensor mounted on an unmanned aerial vehicle (UAV).

Discrete-time predictive trajectory tracking control for nonholonomic mobile robots with obstacle avoidance

This article presents a tracking control approach with obstacle avoidance for a mobile robot. The control law is composed of two parts. The first is a discrete-time model predictive method-based trajectory tracking control law that is derived using an optimal quadratic algorithm. The second part is the obstacle avoidance strategies that switch according to two different designed obstacle avoidance regions. The controllability of the avoidance control law is analyzed. The simulation results validate the effectiveness of the proposed control law considering both trajectory tracking and obstacle avoidance.

ESO-based path following control for underactuated vehicles with the safety prediction obstacle avoidance mechanism

This note investigates the waypoints-based path following problem of underactuated surface vehicles (USVs), considering that there exists the moving obstacle around the reference path. An improved dynamic virtual ship (DVS) guidance principle is proposed by incorporating the safety prediction obstacle avoidance (SPOA) strategy. In the mechanism, a real-time distance function is established to obtain the distance to closest point of approach (DCPA) and time to closest point of approach (TCPA), which are employed to evaluate the current sailing situation. Then the own ship could choose the corresponding sailing mode: path following mode or obstacle avoidance mode. Especially for the latter one, the velocity and the heading angle orders are taken into account together to generate the reasonable avoidance order, which is consistent with the International Regulations of Preventing Collisions at Sea (COLREGs) and the marine practice. Furthermore, based on the full-state observerable characteristic of the underactuated system, the ESO-based output feedback control algorithm is derived to guarantee the convergence of the own ship to the DVS. And the external disturbance and the model uncertainty are integrated as an augmented variable to be estimated. Besides, all signals in the closed-loop system are ensured to be semi-global uniformly ultimately bounded (SGUUB). The effectiveness and robustness of the proposed scheme are verified by the comparative experiment and the experiment within the simulated ocean environment.

Deep Recurrent Neural Networks Based Obstacle Avoidance Control for Redundant Manipulators.

Obstacle avoidance is an important subject in the control of robot manipulators, but is remains challenging for robots with redundant degrees of freedom, especially when there exist complex physical constraints. In this paper, we propose a novel controller based on deep recurrent neural networks. By abstracting robots and obstacles into critical point sets respectively, the distance between the robot and obstacles can be described in a simpler way, then the obstacle avoidance strategy is established in form of inequality constraints by general class-K functions. Using minimal-velocity-norm (MVN) scheme, the control problem is formulated as a quadratic-programming case under multiple constraints. Then a deep recurrent neural network considering system models is established to solve the QP problem online. Theoretical conduction and numerical simulations show that the controller is capable of avoiding static or dynamic obstacles, while tracking the predefined trajectories under physical constraints.

Vision-Based Obstacle Avoidance Strategies for MAVs Using Optical Flows in 3-D Textured Environments.

Due to payload restrictions for micro aerial vehicles (MAVs), vision-based approaches have been widely studied with their light weight characteristics and cost effectiveness. In particular, optical flow-based obstacle avoidance has proven to be one of the most efficient methods in terms of obstacle avoidance capabilities and computational load; however, existing approaches do not consider 3-D complex environments. In addition, most approaches are unable to deal with situations where there are wall-like frontal obstacles. Although some algorithms consider wall-like frontal obstacles, they cause a jitter or unnecessary motion. To address these limitations, this paper proposes a vision-based obstacle avoidance algorithm for MAVs using the optical flow in 3-D textured environments. The image obtained from a monocular camera is first split into two horizontal and vertical half planes. The desired heading direction and climb rate are then determined by comparing the sum of optical flows between half planes horizontally and vertically, respectively, for obstacle avoidance in 3-D environments. Besides, the proposed approach is capable of avoiding wall-like frontal obstacles by considering the divergence of the optical flow at the focus of expansion and navigating to the goal position using a sigmoid weighting function. The performance of the proposed algorithm was validated through numerical simulations and indoor flight experiments in various situations.

A Time-Efficient Co-Operative Path Planning Model Combined with Task Assignment for Multi-Agent Systems

Dealing with uncertainties along with high-efficiency planning for task assignment problem is still challenging, especially for multi-agent systems. In this paper, two frameworks—Compromise View model and the Nearest-Neighbour Search model—are analyzed and compared for co-operative path planning combined with task assignment of a multi-agent system in dynamic environments. Both frameworks are capable of dynamically controlling a number of autonomous agents to accomplish multiple tasks at different locations. Furthermore, these two models are capable of dealing with dynamically changing environments. In both approaches, the Particle Swarm Optimization-based method is applied for path planning. The path planning approach combined with the obstacle avoidance strategy is integrated with the task assignment problem. In one framework, the Compromise View model is used for completing the tasks and a combination of clustering method with the Nearest-Neighbour Search model is used to assign tasks to the other framework. The frameworks are compared in terms of computational time and the resulting path length. Results indicate that the Nearest-Neighbour Search model is much faster than the Compromise View model. However, the Nearest-Neighbour Search model generates longer paths to accomplish the mission. By following the Nearest-Neighbour Search approach, agents can successfully accomplish their mission, even under uncertainties such as malfunction of individual agents. The Nearest-Neighbour Search framework is highly effective due to its reactive structure. As per requirements, to save time, after completing its own tasks, one agent can complete the remaining tasks of other agents. The simulation results show that the Nearest-Neighbour Search model is an effective and robust way of solving co-operative path planning combined with task assignment problems.

Metal Rubber Blank Automatic Laying Obstacle Avoidance Strategy

The new metal rubber blank automatic laying equipment solves the technical problem of preparing large-sized metal rubber sheet components and metal rubber component blanks with complicated configurations such as holes. Based on the automatic laying process of metal rubber, the metal rubber components are divided into simple configuration and complex configuration, and a new method for judging the feasible laying path of metal rubber is proposed. Based on matlab, a new type of rapid metal rubber blank laying obstacle avoidance strategy was designed, which realized the identification and positioning of the feasible path of metal rubber blank automatic laying, which provided technical support for path planning and automatic laying.

Optimal Path-Planning of Nonholonomic Terrain Robots for Dynamic Obstacle Avoidance Using Single-Time Velocity Estimator and Reinforcement Learning Approach

A single-time velocity estimator-based reinforcement learning (RL) algorithm, integrated with a chaotic metaheuristic optimization technique is proposed in this article for the optimal path-planning of the nonholonomic robots considering a moving/stationary obstacle avoidance strategy. The additional contribution of the present study is by employing the Terramechanics principles to incorporate the effects of wheel sinkage into the deformable terrain on the dynamics of the robot aiming to find the optimal compensating force/torque magnitude to sustain a robust and smooth motion. The designed systematic control-oriented system incorporates a cost function of weighted components associated with the target-tracking and the obstacle avoidance. The designed velocity estimator contributes to the finite-state Markov decision process (MDP) in order to train the transition probabilities of the problem objectives. Based on the obtained results, the optimal solution for the Q-learning in terms of the adjusting factor for the minimized tracking error and obstacle collision risk propagation profiles is found at 0.22. The results further confirm the promising capacity of the proposed optimization-based RL algorithm for the collision avoidance control of the nonholonomic robots on deformable terrains.

Research on Obstacle Avoidance Strategy for Welding Robot

Research on Obstacle Avoidance Strategy for Welding Robot

Research on Arbitrary Formation Control of Multiple Robots in Obstacle Environment

To overcome the multi-robots form arbitrary formation in obstacle environment, we propose a control algorithm that combines target allocation algorithm and obstacle avoidance strategy. Firstly, we express the distance between the position of robots and target points by distance information matrix, thus ensure each robot find the corresponding target point. The key idea of the algorithm is to avoid robots from detours and reduce the possibility of collisions between robots. Secondly, the obstacle avoidance is achieved by improving the artificial potential field method integrated with the strategy of moving along the periphery of obstacles. Finally, a simulation environment is established by pygame modules. Simulation results show that the proposed method is feasible and effective.

Constrained generalized predictive control for obstacle avoidance in a quadcopter

SUMMARYThis work proposes a strategy for position control and obstacle avoidance in a quadcopter based on constrained generalized predictive control and geometric attitude control. The approach allows real-time trajectory tracking using optimal control actions and avoids collisions with static obstacles whose position is known. An experimental validation of the proposed controller is presented.

Range Sensor-Based Efficient Obstacle Avoidance through Selective Decision-Making.

In this paper, we address a collision avoidance method for mobile robots. Many conventional obstacle avoidance methods have been focused solely on avoiding obstacles. However, this can cause instability when passing through a narrow passage, and can also generate zig-zag motions. We define two strategies for obstacle avoidance, known as Entry mode and Bypass mode. Entry mode is a pattern for passing through the gap between obstacles, while Bypass mode is a pattern for making a detour around obstacles safely. With these two modes, we propose an efficient obstacle avoidance method based on the Expanded Guide Circle (EGC) method with selective decision-making. The simulation and experiment results show the validity of the proposed method.