Velocity Obstacle Based on Vertical Ellipse for Multi-Robot Collision Avoidance

Service robots operating in domestic indoor environments must be endowed with a safe collision avoidance and navigation method that is reactive enough to avoid contacts with the furniture of the apartment and humans that suddenly appear in front of the robot. Moreover, the method should be local, i.e. should not need a predefined map of the environment. In this paper we describe a navigation and collision avoidance method which is all of that: safe, fast, and local. Based on a geometric grid representation which is derived from the laser range finder of our domestic robot, a path to the next target point is found by employing A*. The obstacles which are used in the local map of the robot are extended depending on the speed the robot travels at. We compute a triangular area in front of the robot which is guaranteed to be free of obstacles. This triangle serves as the space of feasible solutions when searching for the next drive commands. With this triangle, we are able to decouple the path search from the search for drive commands, which tremendously decreases the complexity. We used the proposed method for several years in RoboCup@Home where it was a key factor to our success in the competitions.KeywordsRotational VelocityTarget PointCollision AvoidanceLaser RangeService RobotThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A control strategy for real-time collision avoidance of a mobile robot in an environment containing moving obstacles is proposed. Objects, including the robot, are modelled as convex polyhedra. Collision avoidance is guaranteed if the minimum distance between the robot and the objects is nonzero. A nominal trajectory is assumed to be known from offline planning. The main idea is to change the velocity along the nominal trajectory so that collisions are avoided. Consistency with the nominal plan is desirable. The process is formulated as an optimization problem and a close to optimal solution is obtained. >

When sailing on cluttered water, effective collision avoidance is an essential safety requirement for unmanned surface vehicles (USVs). So that it can avoid multiple random ships effectively. This paper proposes a collision avoidance strategy for USVs based on the probabilistic game theory framework. First, a probability model is established combined with the USV’s kinematics for the collision avoidance problem. Then a greedy algorithm is designed under the framework of probability. It uses a cost function that searches possible movement paths to determine avoidance strategies for the USV. Compared with other collision avoidance methods, the method in this paper seeks to minimize the collision probability instead of guaranteeing no collision, because it is very difficult or impossible to completely avoid the collision in practice. Based on this, our method copes with kinematic constraints of the USV. The effectiveness of the algorithm is verified by simulation, and the simulation results show that the collision avoidance strategy proposed in this paper achieves a very good collision avoidance performance.

With the development of Maritime Autonomous Surface Ships (MASS), considerable research is undertaken to secure their safety. One of the critical aspects of MASS is collision avoidance, and multiple collision avoidance algorithms have been developed. However, due to various reasons, collision avoidance of autonomous merchant vessels appears to be far from resolved. With this study, we aim to discuss the current state of Collision Avoidance Methods (CAMs) and the challenges lying ahead—from a joint academic and practical point of view. To this end, the key Rules from International Regulations for Preventing Collisions at Sea (COLREG) have been reviewed with a focus on their practical application for MASS. Moreover, the consideration of the COLREG Rules in contemporary collision avoidance algorithms has been reviewed. The ultimate objective is to identify aspects of COLREG requiring additional attention concerning MASS developments in terms of collision avoidance. Our conclusions indicate that although a lot of progress has been achieved recently, the feasibility of CAMs for MASS remains questionable. Reasons for so are the ambiguous character of the regulations, especially COLREG, as well as virtually all existing CAMs being at best only partly COLREG-compliant.

A novel intelligent collision avoidance algorithm based on deep reinforcement learning approach for USV

In this study, a method for collision avoidance (CA) in external beam radiation therapy (EBRT) is proposed. The method encompasses the analysis of all positions of the moving components of the beam delivery system, such as the treatment table and gantry, including patient specific information obtained from the computed tomography (CT) images. This method eliminates the need for time-consuming dry runs prior to the actual treatments. This method includes a rigorous computer simulation and CA check prior to each treatment. With this treatment simulation, it is possible to quantify and graphically represent all positions and corresponding trajectories of all points of the moving parts during treatment delivery. The development of the workflow includes several steps: (a) derivation of combined dynamic equation of motion of the EBRT delivery systems, (b) developing the simulation model capable of drawing the motion trajectories of the specific points, (c) developing the interface between the model and the treatment plan parameters, such as couch and gantry parameters for each field. The patient CT images were registered to the treatment couch, so the patient dimensions were included into the simulation. The treatment field parameters were structured in an XML file that was used as an input into the dynamic equations. The trajectories of the moving components were plotted on the same graph using the dynamic equations. If the trajectories intersect, it was the signal that collision exists. This CA method is effective in the simulation of the treatment delivery.

Deep reinforcement learning with dynamic window approach based collision avoidance path planning for maritime autonomous surface ships

As the use of unmanned systems becomes more prevalent in both commercial and military applications, increasing performance requirements have led to a greater demand for automation. The ability for an autonomous unmanned system to perform basic tasks reliably reduces the operator’s cognitive tasks and workload, which could facilitate the control of multiple systems by a single operator. A key component for autonomous systems in many applications is the ability to perform reliable collision avoidance. A critical part of collision avoidance, often overlooked in existing algorithms, is that only a small set of velocities are actually reachable by the platform due to physical limitations or environmental factors. This paper presents the 3D Automated Velocity Obstacle Collision Avoidance (AVOCA) algorithm; a velocity obstacle based collision avoidance system that uses Kinematic Velocity Constraints (KVCs) to bind the velocity selection process. Results for AVOCA are presented from both simulation and experimentation using physical and virtual platforms in a Mixed Reality (MR) environment.

To ensure navigation safety, unmanned surface vehicles (USVs) need to have autonomous collision avoidance capability. A large number of studies on ship collision avoidance are available, and most of these papers assume that the target ships keep straight or follows the International Regulations for Preventing Collisions at Sea (COLREGS). However, in the actual navigation process, the target ship may temporarily turn. Based on the above reasons, this paper proposes a multi-ship collision avoidance decision method for USVs based on the improved velocity obstacle algorithm. In the basic dynamic ship domain model, a collision risk model is constructed to improve the accuracy of the risk assessment between the USV and target ships. The velocity obstacle algorithm is combined with the dynamic ship domain, and the collision avoidance timing and method are judged according to the collision risk. The simulation results show that the decision method can handle the situation that the target ship temporarily turns and has an emergency collision avoidance capability. Compared with the traditional VO algorithm, the collision avoidance time of the method is shorter, and the number of course changes is less.

Currently, precise spraying of sweet potatoes is mainly accomplished through semi-mechanized or single spraying robots, which results in low operating efficiency. Moreover, it is time-consuming and labor-intensive, and the pests and diseases cannot be eliminated in time. Based on multi robot navigation technology, multiple robots can work simultaneously, improving work efficiency. One of the main challenges faced by multi robot navigation technology is to develop a safe and robust collision avoidance strategy, so that each robot can safely and efficiently navigate from its starting position to the expected target. In this article, we propose a low-cost multi-robot collision avoidance method to solve the problem that multiple robots are prone to collision when working in field at the same time. This method has achieved good results in simulation. In particular, our collision avoidance method predicts the possibility of collision based on the robot's position and environmental information, and changes the robot's path in advance, instead of waiting for the robot to make a collision avoidance decision when it is closer. Finally, we demonstrate that a multi-robot collision avoidance approach provides an excellent solution for safe and effective autonomous navigation of a single robot working in complex sweet potato fields. Our collision avoidance method allows the robot to move forward effectively in the field without getting stuck. More importantly, this method does not require expensive hardware and computing power, nor does it require tedious parameter tuning.

Unmanned Aerials Vehicles (UAVs), most known as drones, recently gained a lot of interest in several domains of civil applications. With the number of operating drones expected to quickly rise in the next few years comes the need to develop efficient collision avoidance solutions. To ensure the applicability of the collision avoidance solutions, given the limitations of UAVs, they must rely on a reliable source of information, and must be computationally efficient. This paper aims at providing an implementation of the Velocity Obstacle collision avoidance method, based on the information transmitted by the other UAVs. Multi-agent based simulations using the simulation software AirSim and the multi-agent platform SARL are proposed to assess the validity of the proposed solution.

Road accidents and traffic congestion are challenging issues for global transport systems. Autonomous vehicles and connected vehicles are promising technologies to improve road safety and reduce traffic congestion. In this paper we investigate the performance of connected vehicles and assess the positive impact of connected vehicles on the collaborative road safety applications. To achieve the research goal, we first develop a low cost and scalable connected vehicles testbed, which consists of laptops equipped with Wi-Fi transceivers. The main concern is that collaborative road safety applications need to be widely tested with vehicle to vehicle (V2V) communications. However, the commercial dedicated short-range communications (DSRC) devices are very expensive, which makes it difficult to set up a large connected vehicles testbed. Based on the experiments on the V2V communications, the performance of forward collision avoidance under emergency events, which is a representative collaborative road safety application, is analysed. Interesting insights to the performance of V2V and the improvement of collision avoidance with V2V are obtained. The research works could be used for the analysis of connected vehicles impact on other collaborative roads safety applications.

This paper introduces a new behavior-based collision avoidance approach for mobile robot navigation in unknown and dynamic environments, which called Nearest Virtual-Target NVT. The NVT approach was developed based on a modeling-planning-reaction configuration. In modeling module, sensory information is integrated to construct a local model of environment which represents obstacles distribution and free obstacle areas in a part of robot's work space. The planning module uses the “actual-virtual target switching strategy” to compute obstacle free paths towards the target. The robot motion generation is handled by the reaction module. The reaction module applies a fuzzy controller to control the robot's rotational and translational velocities. The contribution of this approach is solving navigation difficulties presented in previous approaches for successful motion of the robot towards the target in troublesome scenarios such as narrow passages, very dense, cluttered and dynamic environments. Feasibility and effectiveness of the proposed approach are verified through simulation and real robot experiments. Eventually, advantages and limitations of this approach are discussed.

This paper presents a real-time path planning approach for controlling the motion of space-based robots. The algorithm can plan three-dimensional trajectories for agents in a complex environment which includes numerous static and dynamic obstacles, path constraints, and/or performance constraints. This approach is extended based on the dynamic window approach (DWA). As the classic reactive method for obstacle avoidance, DWA uses an optimized function to select the best motion command. The original DWA optimization function consists of three weight terms. Changing the weights of these terms will change the behavior of the algorithm. In this paper, to improve the evaluation ability of the optimization function and the robot’s ability to adapt to the environment, a new optimization function is designed and combined with fuzzy logic to adjust the weights of each parameter of the optimization function. Given that DWA has the defect of local minima, which makes the robot hard to escape U-shaped obstacles, a dual dynamic window method and local goals are adopted in this article to help the robot escape local minima. By comparison, the proposed method is superior to traditional DWA and fuzzy DWA (F_DWA) in terms of computational efficiency, smoothness and security.

According to the characters of marine navigation, this paper extends the concept of the velocity obstacle and develops a reactive approach to collision avoidance among multiple ship agents. By selecting a reasonable velocity within free parts of its maneuvering space that aren’t covered by the union of velocity obstacles of all other ship agents, a ship agent can navigate safely without collision. Simulation experiments show that our approach is able to navigate multiple ship agents with smooth and natural paths to avoid collision, and can be applied to multi-agent based marine traffic simulation systems. INTRODUCTION A simulation-based marine traffic flow analysis is widely used for safety assessment and maritime construction planning such as channel traffic control, port design, and water lane establishment. Simulation models are continuously upgraded with the advent of new computer technologies. The modeling of multi-agent and group behavior to simulate complex marine traffic flow has been gaining increasing attention (Inaishi, 2006). In this area, the motion planning of ship agents is a central problem. In previous works,we have studied how ship agents autonomously make their navigation plans, select routes and avoid collision with static obstacles in the environment (Pan, 2008). This paper further focuses on the collision avoidance among multiple moving ship agents and proposes a velocity obstacle-based approach. The velocity obstacle concept (Fiorini, 1998) is a generally applicable, well-defined and simple technique that has been widely used for safe navigation among moving obstacles in robotics and virtual environments. This paper extends the concept to deal with encounters among multiple ships and develops a reactive collision avoidance model that agrees with marine navigation conventions to the outmost extent. In our approach, all ships navigate independently without explicit communication with each other. This is a simple and natural formulation that is applicable and easy to implement. ICCTP 2009: Critical Issues in Transportation Systems Planning, Development, and Management ©2009 ASCE 1688