Multi-robot Collision Avoidance Research Articles

Multi-robot collision avoidance method in sweet potato fields.

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.

Learning scalable and efficient communication policies for multi-robot collision avoidance

Decentralized multi-robot systems typically perform coordinated motion planning by constantly broadcasting their intentions to avoid collisions. However, the risk of collision between robots varies as they move and communication may not always be needed. This paper presents an efficient communication method that addresses the problem of “when” and “with whom” to communicate in multi-robot collision avoidance scenarios. In this approach, each robot learns to reason about other robots’ states and considers the risk of future collisions before asking for the trajectory plans of other robots. We introduce a new neural architecture for the learned communication policy which allows our method to be scalable. We evaluate and verify the proposed communication strategy in simulation with up to twelve quadrotors, and present results on the zero-shot generalization/robustness capabilities of the policy in different scenarios. We demonstrate that our policy (learned in a simulated environment) can be successfully transferred to real robots.

Non-communicating Decentralized Multi-robot Collision Avoidance in Grid Graph Workspace based on Dueling Double Deep Q-Network

This paper designs a motion rule suitable for grid environment and proposes a multi-robot autonomous obstacle avoidance method based on deep reinforcement learning. The training and validation of the method are done under the Stage simulation platform based on ROS operating system. During the training process, the robot uses Lidar to obtain the surrounding state information and generates actions based on the state information to obtain rewards, and the robot is guided by the rewards to optimize the strategy. Based on the D3QN algorithm, a new reward function is designed, a proximity penalty is introduced to reduce the collision between robots, a distance reward is added to guide the robot to complete the task, a step reward is added to improve the efficiency of the robot to complete the task, and an illegal action penalty is added to avoid the robot to choose an illegal action; the input is 5 frames of Lidar data, and in the network structure, the agent can better learn the correlation between the data by introducing Long Short Term Memory(LSTM) layer, and introducing Convolutional Block Attention Module(CBAM), a hybrid attention mechanism to allow the robot to pay more attention to the information of the surrounding robots. By designing experiments, we demonstrate that the learned strategy can effectively guide the robot through obstacle avoidance and complete the task.

Decentralized Multi-Robot Collision Avoidance: A Systematic Review from 2015 to 2021

An exploration task can be performed by a team of mobile robots more efficiently than human counterparts. They can access and give live updates for hard-to-reach areas such as a disaster site or a sewer. However, they face some issues hindering them from optimal path planning due to the symmetrical shape of the environments. Multiple robots are expected to explore more areas in less time while solving robot localization and collision-avoidance issues. When deploying a multi-robot system, it is ensured that the hardware parts do not collide with each other or the surroundings, especially in symmetric environments. Two types of methods are used for collision avoidance: centralized and decentralized. The decentralized approach has mainly been used in recent times, as it is computationally less expensive. This article aims to conduct a systematic literature review of different collision-avoidance strategies and analyze the performance of innovative collision-avoidance techniques. Different methods such as Reinforcement Learning (RL), Model Predictive Control (MPC), Altruistic Coordination, and other approaches followed by selected studies are also discussed. A total of 17 studies are included in this review, extracted from seven databases. Two experimental designs are studied: empty/open space and confined indoor space. Our analysis observed that most of the studies focused on empty/open space scenarios and verified the proposed model only through simulation. ORCA is the primary method, against which all the state-of-the-art techniques are evaluated. This article provides a comparison between different methods used for multi-robot collision avoidance. It discusses if the methods used are focused on safety or path planning. It also sheds light on the limitations of the studies included and possible future directions.

Decentralized Path Planning for Multi-Objective Robot Swarm System

The multi-robot path planning aims to explore a set of non-colliding paths with the shortest sum of lengths for multiple robots. The most popular approach is to artificially decompose the map into discrete small grids before applying heuristic algorithms. To solve the path planning in continuous environments, we propose a decentralized two-stage algorithm to solve the path-planning problem, where the obstacle and inter-robot collisions are both considered. In the first stage, an obstacle- avoidance path-planning problem is mathematically developed by minimizing the travel length of each robot. Specifically, the obstacle-avoidance trajectories are generated by approximating the obstacles as convex-concave constraints. In the second stage, with the given trajectories, we formulate a quadratic programming (QP) problem for velocity control using the control barrier and Lyapunov function (CBF-CLF). In this way, the multi-robot collision avoidance as well as time efficiency are satisfied by adapting the velocities of robots. In sharp contrast to the conventional heuristic methods, path length, smoothness and safety are fully considered by mathematically formulating the optimization problems in continuous environments. Extensive experiments as well as computer simulations are conducted to validate the effectiveness of the proposed path-planning algorithm.

Decentralized Multi-Robot Collision Avoidance in Complex Scenarios With Selective Communication

Deep reinforcement learning has been demonstrated to be an effective solution to the multi-robot collision avoidance problem. However, with existing methods, robots typically generate actions only based on local observations, sometimes augmented with global communication. Their performance deteriorates in limited bandwidth environments and complex scenarios with various obstacles and high robot density. We propose SelComm, a selective communication framework to generate cooperative and collision-free actions for robots in multi-robot navigation tasks. Specifically, we develop a decentralized message selector, enabling each robot to calculate relations with other robots using both agent-level information and sensor-level information, and select the most valuable messages to meet the bandwidth limitation. Then we introduce the attentional communication channel for efficient communication. Our experimental evaluations based on various scenarios demonstrate that SelComm learns more cooperative behaviors and outperforms state-of-the-art methods in limited bandwidth environments and complex scenarios.

Distributed Multi-robot Collision Avoidance Using the Voronoi-based Method

Collision avoidance is a fundamental problem in multi-robot motion planning, enabling robots to coordinate in a safe and efficient manner. In this paper, we introduce several best-known distributed collision avoidance algorithms and present the Voronoi-based method in detail, which assigns optimal dominance regions for robots using the Voronoi diagram, constrains robot motions within the buffered Voronoi diagram, and follows right-hand rule when deadlock happens during navigating to the goals. A series of simulations are conducted to demonstrate the efficacy of collision avoidance guarantee under robot localization uncertainty while avoiding deadlock using our presented algorithm. We claim that such a method is superior to most of the existing distribution methods in a known environment in efficiency of implementation.

Prioritized planning algorithm for multi-robot collision avoidance based on artificial untraversable vertex

This paper presents a method to avoid collisions and deadlocks between mobile robots working collaboratively in a shared physical environment. Based on the shared knowledge of the robot’s direction and coordinates, we define five conflict types between robots and propose a new concept named Artificial Untraversable Vertex (AUV) to resolve the potential conflicts. Since conflict avoidance between robots is typically a real-time process, a heuristic search algorithm D* Lite with fast replanning characteristics is introduced. Once a robot finds that it may collide with another robot while moving along the preplanned path, a new conflict-free path can be calculated based on the AUV and D* Lite. The experimental results demonstrate that the proposed Multi-Robot Path Planning (MRPP) method can effectively avoid collisions and deadlocks between mobile robots.

Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments

This letter presents a data-driven decentralized trajectory optimization approach for multi-robot motion planning in dynamic environments. When navigating in a shared space, each robot needs accurate motion predictions of neighboring robots to achieve predictive collision avoidance. These motion predictions can be obtained among robots by sharing their future planned trajectories with each other via communication. However, such communication may not be available nor reliable in practice. In this letter, we introduce a novel trajectory prediction model based on recurrent neural networks (RNN) that can learn multi-robot motion behaviors from demonstrated trajectories generated using a centralized sequential planner. The learned model can run efficiently online for each robot and provide interaction-aware trajectory predictions of its neighbors based on observations of their history states. We then incorporate the trajectory prediction model into a decentralized model predictive control (MPC) framework for multi-robot collision avoidance. Simulation results show that our decentralized approach can achieve a comparable level of performance to a centralized planner while being communication-free and scalable to a large number of robots. We also validate our approach with a team of quadrotors in real-world experiments.

Fpga Based Multi-Robot Collision Avoidance System

This paper presents a Multi-robot collision avoidance system suitable for FPGA implementation. The proposed scheme attempts a novel method of Reciprocal Collision Avoidance(RCA) along with Accelerating Velocity Obstacles(AVO). Parallel architecture is used for developing the collision analysis of robots with different targets. Each of these robots moves and reaches its target, avoiding collisions on its path. Simulations for the digital design hardware have been carried out in Vivado software and the robotic movements have been demonstrated using V-rep software. The proposed scheme would result in reduced cost and power dissipation while deploying in FPGAs. The details of the collision detection algorithm and the working of different modules used in the scheme along with test results are presented in the paper.

Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network.

This paper presents a novel decentralized multi-robot collision avoidance method with deep reinforcement learning, which is not only suitable for the large-scale grid map workspace multi-robot system, but also directly processes Lidar signals instead of communicating between the robots. According to the particularity of the workspace, we handcrafted a reward function, which considers both the collision avoidance among the robots and as little as possible change of direction of the robots during driving. Using Double Deep Q-Network (DDQN), the policy was trained in the simulation grid map workspace. By designing experiments, we demonstrated that the learned policy can guide the robot well to effectively travel from the initial position to the goal position in the grid map workspace and to avoid collisions with others while driving.

Distributed Non-Communicating Multi-Robot Collision Avoidance via Map-Based Deep Reinforcement Learning.

It is challenging to avoid obstacles safely and efficiently for multiple robots of different shapes in distributed and communication-free scenarios, where robots do not communicate with each other and only sense other robots’ positions and obstacles around them. Most existing multi-robot collision avoidance systems either require communication between robots or require expensive movement data of other robots, like velocities, accelerations and paths. In this paper, we propose a map-based deep reinforcement learning approach for multi-robot collision avoidance in a distributed and communication-free environment. We use the egocentric local grid map of a robot to represent the environmental information around it including its shape and observable appearances of other robots and obstacles, which can be easily generated by using multiple sensors or sensor fusion. Then we apply the distributed proximal policy optimization (DPPO) algorithm to train a convolutional neural network that directly maps three frames of egocentric local grid maps and the robot’s relative local goal positions into low-level robot control commands. Compared to other methods, the map-based approach is more robust to noisy sensor data, does not require robots’ movement data and considers sizes and shapes of related robots, which make it to be more efficient and easier to be deployed to real robots. We first train the neural network in a specified simulator of multiple mobile robots using DPPO, where a multi-stage curriculum learning strategy for multiple scenarios is used to improve the performance. Then we deploy the trained model to real robots to perform collision avoidance in their navigation without tedious parameter tuning. We evaluate the approach with multiple scenarios both in the simulator and on four differential-drive mobile robots in the real world. Both qualitative and quantitative experiments show that our approach is efficient and outperforms existing DRL-based approaches in many indicators. We also conduct ablation studies showing the positive effects of using egocentric grid maps and multi-stage curriculum learning.

Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios

Developing a safe and efficient collision-avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generates its paths with limited observation of other robots’ states and intentions. Prior distributed multi-robot collision-avoidance systems often require frequent inter-robot communication or agent-level features to plan a local collision-free action, which is not robust and computationally prohibitive. In addition, the performance of these methods is not comparable with their centralized counterparts in practice. In this article, we present a decentralized sensor-level collision-avoidance policy for multi-robot systems, which shows promising results in practical applications. In particular, our policy directly maps raw sensor measurements to an agent’s steering commands in terms of the movement velocity. As a first step toward reducing the performance gap between decentralized and centralized methods, we present a multi-scenario multi-stage training framework to learn an optimal policy. The policy is trained over a large number of robots in rich, complex environments simultaneously using a policy-gradient-based reinforcement-learning algorithm. The learning algorithm is also integrated into a hybrid control framework to further improve the policy’s robustness and effectiveness. We validate the learned sensor-level collision-3avoidance policy in a variety of simulated and real-world scenarios with thorough performance evaluations for large-scale multi-robot systems. The generalization of the learned policy is verified in a set of unseen scenarios including the navigation of a group of heterogeneous robots and a large-scale scenario with 100 robots. Although the policy is trained using simulation data only, we have successfully deployed it on physical robots with shapes and dynamics characteristics that are different from the simulated agents, in order to demonstrate the controller’s robustness against the simulation-to-real modeling error. Finally, we show that the collision-avoidance policy learned from multi-robot navigation tasks provides an excellent solution for safe and effective autonomous navigation for a single robot working in a dense real human crowd. Our learned policy enables a robot to make effective progress in a crowd without getting stuck. More importantly, the policy has been successfully deployed on different types of physical robot platforms without tedious parameter tuning. Videos are available at https://sites.google.com/view/hybridmrca.

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

Bounding volume based approaches in velocity obstacle (VO) provide a good solution for collision avoidance of mobile robots with uncertainty. However, the VO built with the bounding footprint always has over-constraining problems which may lead to conservative maneuvers of the mobile robots. Addressing this problem, a vertical ellipse based velocity obstacle (VEVO) collision avoidance method is proposed in this paper. The method mitigates the over-constraining situation by building the footprint probability ellipse whose minor axis is vertical to the direction of the obstacle to minimize the VO area. Based on VEVO, a DWA (Dynamic Window Approach) integrated method is proposed to provide a set of available velocities in speed selection. According to different collision avoidance objectives like collision safety, shortest time consumption and shortest trajectory length, a multi-objective velocity selecting strategy is proposed to provide optimal velocities for motion planning. Furthermore, a dynamic local path adjustment method is proposed to help robots react to the closest obstacle (dynamic or static) according to different collision safety requirements. We validate our methods in a simulated workspace with different numbers of robots going to their goal points. Experimental results show VEVO method could improve the collision avoidance performance in crowded multi-robot environment and robots could achieve their different objectives when suitable parameters are set in the velocity evaluation function. The proposed dynamic local path adjustment method only affects the trajectories in local areas and could ensure collision avoidance safety and performance at the same time.

A Discrete Event Formulation for Multi-Robot Collision Avoidance on Pre-planned Trajectories

In this paper we consider the problem of collision avoidance among robots that follow pre-planned trajectories in a structured environment while minimizing the maximum traveling time among them. More precisely, we consider a discrete event formulation of this problem. Robots are modeled by automata, the environment is partitioned into a square grid where cells represent free space, obstacles and walls, which are modeled as shared resources among robots. The main contribution of this paper is twofold. First, we propose a problem formulation based on mixed integer linear programming to compute an optimal schedule for the pre-planned trajectories. Second, we propose a heuristic method to compute a sub-optimal schedule: the computational complexity of this approach is shown to be polynomial with the number of robots and the dimension of the environment. Finally, simulations are provided to validate performance and scalability of the proposed approach.

ITC: Infused Tangential Curves for Smooth 2D and 3D Navigation of Mobile Robots †

Navigation is an indispensable component of ground and aerial mobile robots. Although there is a plethora of path planning algorithms, most of them generate paths that are not smooth and have angular turns. In many cases, it is not feasible for the robots to execute these sharp turns, and a smooth trajectory is desired. We present ‘ITC: Infused Tangential Curves’ which can generate smooth trajectories for mobile robots. The main characteristics of the proposed ITC algorithm are: (1) The curves are tangential to the path, thus maintaining continuity, (2) The curves are infused in the original global path to smooth out the turns, (3) The straight segments of the global path are kept straight and only the sharp turns are smoothed, (4) Safety is embedded in the ITC trajectories and robots are guaranteed to maintain a safe distance from the obstacles, (5) The curvature of ITC curves can easily be controlled and smooth trajectories can be generated in real-time, (6) The ITC algorithm smooths the global path on a part-by-part basis thus local smoothing at one point does not affect the global path. We compare the proposed ITC algorithm with traditional interpolation based trajectory smoothing algorithms. Results show that, in case of mobile navigation in narrow corridors, ITC paths maintain a safe distance from both walls, and are easy to generate in real-time. We test the algorithm in complex scenarios to generate curves of different curvatures, while maintaining different safety thresholds from obstacles in vicinity. We mathematically discuss smooth trajectory generation for both 2D navigation of ground robots, and 3D navigation of aerial robots. We also test the algorithm in real environments with actual robots in a complex scenario of multi-robot collision avoidance. Results show that the ITC algorithm can be generated quickly and is suitable for real-world scenarios of collision avoidance in narrow corridors.

Two Adaptive Communication Methods for Multi-Robot Collision Avoidance

SummaryDesigners of robotic groups are faced with the formidable task of creating effective coordination architectures that can deal with collisions due to changing environment conditions and hardware failures. Communication between robots is a mechanism that can at times be helpful in such systems, but can also create a time, energy, or computation overhead that reduces performance. In dealing with this issue, different communication schemes have been proposed ranging from those without any explicit communication, localized algorithms, and centralized or global communicative methods. Finding the optimal communication act is typically an intractable problem in real-world problems. As a result, we argue that at times group designers should use computationally bounded team communication approaches. We propose two such approaches: an algorithm selection approach to communication whereby robots choose between a known group of communication schemes and a parameterized communication framework whereby robots can reason about how large a communication radius is needed for a given problem. Both solutions use a novel coordination cost measure, combined coordination costs, to find the appropriate level of communication within such groups. Robots can then use this measure to create adaptive communication approaches that select between communication approaches as needed during task execution. We validated this approach through conducting extensive experiments in a canonical robotic foraging domain and found that robotic groups using these adaptive methods were able to significantly increase their productivity compared to teams that used only one type of communication scheme.

Multi robot collision avoidance in a shared workspace

This paper presents a decentralised human-aware navigation algorithm for shared human–robot work-spaces based on the velocity obstacles paradigm. By extending our previous work on collision avoidance, we are able to include and avoid static and dynamic obstacles, no matter whether they are induced by other robots and humans passing through. Using various cost maps and Monte Carlo sampling with different cost factors accounting for humans and robots, the approach allows human workers to use the same navigation space as robots. It does not rely on any external positioning sensors and shows its feasibility even in densely packed environments.

A laser-based multi-robot collision avoidance approach in unknown environments

As a fundamental problem, collision avoidance for multiple robots still need further investigation, especially for many robots aggregating in a tight space. In this article, a laser-based collision avoidance approach is proposed in complex multi-robot environments. The laser data is analyzed and processed in terms of distance thresholding, safe passageway analysis, obstacles repulsion, goal position attraction, and inter-robot safety. Specifically, the safe passageway analysis is used to remove unsafe directions effectively, and inter-robot safety processing reduces the possibility of being selected for the directions affected by the neighboring robots. On this basis, an optimized decision is made to guarantee that the robots achieve collision-free motions even in crowded environments. The validity of the proposed approach is verified by simulations.

Decentralized safe conflict resolution for multiple robots in dense scenarios

Multi-robot conflict resolution is a challenging problem, especially in dense environments where many robots must operate safely in a confined space. Centralized solutions do not scale well with the number of robots in dynamic scenarios: a centralized communication can cause bottlenecks and may not be robust enough when channels are unreliable; the complexity of algorithms grows with the number of robots, making online re-computation too expensive in many situations. In this work, we propose a decentralized approach for conflict resolution where robots show reactive and safe behaviors, avoiding collisions with both static and dynamic objects, even under unreliable communication conditions and with low resources. They detect conflicts with neighboring obstacles locally and then apply rules to surround them in a roundabout fashion, assuming that others will follow the same policy. The method is designed for unicycle robots with range-finder sensors, and it is able to cope with noisy sensors and second-order dynamic constraints, ensuring always collision-free navigation. Besides, a set of metrics and scenarios for benchmarking in multi-robot collision avoidance are proposed. We also compare our method with others from the state of the art through extensive simulations. Experiments with real robots are also presented in order to show the feasibility of the system.