Collision Avoidance System Synthesis for a Group of Robots in Unsupervised Learning Paradigm

This paper presents a new design for formation control on a group of autonomous humanoid robots with obstacle and collision avoidance ability that inspired by human walking behavior in a pedestrian crowd. This human walking behavior model is known as Social Force Model (SFM) and has been widely used to predict individual movement in a crowd in many variety of situation. We combine consensus algorithm with virtual structure approach for formation control and SFM for obstacle and collision avoidance. In this research, we induced some factors in SFM into consensus equation and then implemented into a group of humanoid robots. The aim of the integration is to create a group of robots that are capable of carrying out its collective tasks while still able to maintain its safety. The use of perception effect, distinct obstacle and collision avoidance function on the algorithm will differentiate algorithm with the others. The attractive feature of this new design is the various behaviors of robots to go back to their initial formation after they avoid obstacles. In the case of robot is trapped in a crowded situation (singularity condition), robot will still trying to look a new position, until it find a condition that allow him to move forward. We verify the proposed algorithm by some simulations and experiments.

This paper focuses on decentralized coordination for small or medium groups of heterogeneous mobile robots with relatively low computational resources. Specifically, we consider coordinated obstacle avoidance techniques for mobile platforms performing high level tasks, such as patrolling or exploration. In more details, we propose the use of a greedy kinodynamic collision avoidance approach for the single robots and the use of the the Max-sum algorithm for multi-robot coordination. The system implementation and its testing are based on the popular robot middleware ROS and the gazebo simulation environment. Obtained results show that our distributed collision avoidance approach is able to achieve safe navigation in real-time with a very low overhead in terms of computation and communication.KeywordsCollision AvoidanceLocal GoalFactor GraphRobot PositionGlobal GoalThese 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.

To cope with the problem of repeatedly triggering collision avoidance conditions that collision avoidance algorithms used in containment control systems, this article investigates the reconfiguration of communication network topology for the multi-unmanned surface vehicle (USV) containment control system, which is from the perspective of algebraic connectivity of the system topology. By analyzing the relationship between the algebraic connectivity of the network topology composed of followers and the converging positions of followers and considering the capability of the system to resist external disturbances and avoid collisions within the system, a multi-USV containment control system topology reconfiguration strategy based on the algebraic connectivity is proposed. The strategy regards the desired algebraic connectivity as the control objective. By identifying the USVs involved in the cooperative task and their communication links in a decentralized way, each USV in the system is able to independently add and delete communication links, thus obtaining a system topology that matches the control objective. Under the reconfigured system topology, the final convergence position of the followers is relatively dispersed. Systems with such characteristics have better collision avoidance and antidisturbance properties, which can compensate to a certain extent for the limitations of traditional correlation algorithms under the influence of complex marine environments. Finally, the simulation and experimental results validate the effectiveness of the topology reconfiguration strategy proposed in this article for multi-USV containment control systems.

Unmanned Aerial Vehicles (UAVs), or drones, have recently become a favorable solution for fast parcel delivery due to their maneuverability and advances in navigation technologies. With the limitation of battery capacity and payload of drones, it is crucial to consider both efficiency and cost while conducting the tasks. Meanwhile, UAVs should not collide with each other while traveling to customers. In this article, we propose a UAV parcel delivery system involving deep reinforcement learning (DRL) approach for collision avoidance and a genetic algorithm for route optimization. Specifically, a delivery center generates near-optimal routes, loading UAV with parcels according to demands. Each UAV takes charge of delivering packages in compliance with the assigned route while avoiding collision with each other. We utilize DRL to achieve collision avoidance without having prior knowledge about the trajectories of other UAVs. Additionally, we adopt a genetic algorithm to obtain the lowest energy cost path for each UAV. To find such an optimized path, we solve a capacitated vehicle routing problem (CVRP) with a modified cost function and extra constraints. Realistic simulations using a physics engine and software-in-the-loop (SITL) are conducted to evaluate the feasibility of the proposed methods.

Safety is a primary concern for the various transport means. For sea transport, this includes various aspects like human safety at sea and at port, and also environmental safety and sustainability. In heavy-traffic regions where the waters are congested and vessels sail very closely together, ensuring these safety needs can be challenging. In this paper, we leverage on the rich information transmitted through the automatic identification system (AIS) and propose, for the first time, an integrated simulation-optimization approach for real time collision avoidance. This enables capturing of stochastic dynamic behavior of vessels for better prediction and fast trajectory optimization for application in real time. Specifically, a realistic agent-based model is developed based on behavioral learning in a real-environment, and incorporated into a fast collision avoidance optimization model in real time to provide robust collision avoidance that is able to account for future stochastic consequences of the actions taken. To achieve this, we develop: 1) a vessel pattern recognition method that mines the rich AIS data to produce realistic trajectory models; 2) an agent-based simulation model to enhance future trajectory prediction; and 3) a fast surrogate-based sampling technique to generate collision avoidance maneuvers for vessel captains in real time. To illustrate the feasibility of the approach, we use the case of the Singapore strait, one of the busiest straits in the world.

This paper considers a rendezvous problem, where a group of wheeled mobile robots with sensing and power constraints is tasked to meet at a common destination. Each robot is modeled in the wheel kinematic level, which is governed by the wheel actuation power constraints. The group of robots is of a leader-follower network structure, where only the leader robot is aware of the desired destination and the follower robots are driven by the leader to the common destination via local sensing of neighboring robots. To ensure the availability of inter-robot communication, the motion of robots is constrained to preserve network connectivity, enabling leader-based guidance via connected paths. In addition, the motion of robots is further constrained to avoid collisions with other robots. To achieve these objectives, a guidance function based decentralized controller is developed to control the wheel velocities of each robot, which ensures global convergence to the destination while guaranteeing the network connectivity, collision avoidance, and not violating its sensing and actuator power capabilities. The simulation results demonstrate the effectiveness of the developed controller.

Recognizing aspects of articulation from audio recordings of speech is an important problem, either as an end in itself or as part of an articulatory approach to automatic speech recognition. In this paper we study the frame-level classification of a set of articulatory features (AFs) inspired by the vocal tract variables of articulatory phonology. We compare k nearest neighbor (k-NN) classifiers and multilayer perceptrons (MLPs), using different acoustic feature vectors, and classify the AFs either independently or jointly. We also consider using the MLP outputs for all of the AFs as inputs to k-NN classifiers for the individual AFs, effectively using the MLPs as a form of nonlinear dimensionality reduction and allowing the decision for each AF to be based on the MLPs for the other AFs. We find that MLPs outperform k-NN classifiers, while k-NN classifiers using MLP outputs outperform both. Index Terms: articulatory modeling, speech inversion, multilayer perceptron, k nearest neighbors

A formulation that makes possible the integration of collision prediction and avoidance stages for mobile robots moving in general terrains containing moving obstacles is presented. A dynamic model of the mobile robot and the dynamic constraints are derived. Collision avoidance is guaranteed if the distance between the robot and a moving obstacle is nonzero. A nominal trajectory is assumed to be known from off-line planning. The main idea is to change the velocity along the nominal trajectory so that collisions are avoided. A feedback control is developed and local asymptotic stability is proved if the velocity of the moving obstacle is bounded. Simulation results verify the value of the proposed strategy. >

An integrated collision prediction and avoidance scheme for mobile robots in non-stationary environments

This paper presents an approach to coordinating a group of mobile robots that move along the designed paths. Subject to the constraints of velocity/acceleration bounds and collision avoidance, the robots are required to maintain the formation relationship while moving. The coordination is realized by posing the coordination problem as a velocity optimization problem in motion planning and then properly planning robots' velocities along the paths. The linear interactive and general optimizer (lingo) is utilized to achieve the velocity optimization goal. Simulations are performed on a group of mobile robots to demonstrate the effectiveness of the proposed approach in coordinated motion planning with the formation requirement.

A flexible operation of multiple robotic manipulators operating in a dynamic environment requires online trajectory planning to ensure collision-free trajectories. In this work, we propose a real-time capable motion control algorithm, based on nonlinear model predictive control, which accounts for static and dynamic obstacles. The proposed algorithm is realized in a distributed scheme, where each robot optimizes its own trajectory with respect to the related objective and constraints. We propose a novel approach for collision avoidance between multiple robotic manipulators, where each robot accounts for the predicted movement of the neighboring robots. Additionally, we propose a method to reliably detect and resolve deadlocks occurring in a setup of multiple robotic manipulators. We validate our approach on pick and place scenarios involving multiple robotic manipulators operating in a common workspace in a realistic simulation environment set up in Gazebo. The robots are controlled using the Robot Operating System. Our approach scales up to 4 manipulators and computes a path for each robot in a simultaneous pick and place operation in 94% of all investigated cases without deadlock detection and 100 % of cases with the proposed deadlock resolution algorithm. In contrast, the investigated conventional path planners, such as PRM, PRM*, CHOMP and RRT-Connect, successfully plan a trajectory in at most 54% of all investigated cases for a simultaneous operation of 4 robotic manipulators hindering their application in setups of multiple manipulators.

The method to organize a safe and optimal joint movement of a group of intelligent mobile robots that solve common tasks in a potentially dangerous territory is purpose. Such territories include: territory covered by fire, chemically contaminated territory, and another territory with the manifestation of an emergency in which robots will be of high utility. To solve this problem, a software platform for organizing group interactions of mobile objects has been developed and the principles of building its modular architecture are given. Using the platform, the developed technique for solving the problem was implemented and a series of experiments was conducted to evaluate its effectiveness. The technique is based on algorithms for efficiently representing the movement space in the form of a directed graph, finding the shortest path based on the a-star algorithm with an optimal heuristic function, and the logic of joint interaction of a group of mobile robots with the possibility of task distribution. Evaluation of the effectiveness of the developed method was carried out on the basis of a generalized method for calculating the stabilized value of the indication of the effectiveness criterion. A demonstration experiment is the task of simultaneously and safely collecting a group of robots in a target area in a potentially dangerous territory. The main parameter to be evaluated is simultaneity of the arrival of a group of robots depending on the number of robots in a group.

Multi-agent Robots Systems (MARS) can be defined as sets of autonomous robots coordinated through a communication system to achieve cooperative tasks. During the last 20 years, MARS have found a wide range of applications in terrestrial, spatial and oceanic explorations emerging as a new research area (Cao et al. (1997)). Some advantages can be obtained from the collective behavior of MARS. For instance, the kind of tasks that can be accomplished are inherently more complex than those a single robot can accomplish. Also, the system becomes more flexible and fault-tolerant (Yamaguchi (2003)). The range of applications includes toxic residues cleaning, transportation and manipulation of large objects, alertness and exploration, searching and rescue tasks and simulation of biological entities behaviors (Arai et al. (2002)). The study ofMARS extends the classical problems of single robotswith new issues likemotion coordination, task decomposition and task assignment, network communications, searching and mapping, etc. Therefore, the study of MARS encompass distributed systems, artificial intelligence, game theory, biology, ethology, economics, control theory, etc. Motion coordination is an important research area of MARS, specifically formation control (Chen & Wang (2005)). The main goal is to coordinate a group of mobile agents or robots to achieve a desired formation pattern avoiding inter-agent collisions at the same time. The formation strategies are decentralized because it is assumed that every agent measures the position of a certain subset of agents and, eventually, it detects the position of other agents when a minimal allowed distance is violated and collision danger appears. Thus, the main intention is to achieve desired global behaviors through local interactions (Francis et al. (2004)). Also, the decentralized approaches offer greater autonomy for the robots, less computational load in control implementations and its applicability to large scale groups (Do (2007)). According to Desai (2002); Muhammad & Egerstedt (2004), the possible inter-agent communications and the desired relative position of every agent with respect to the others can be represented by a FormationGraph (FG). The application of different FG’s to the same group of robots produces different dynamics on the team behavior. In the literature, some special FG topologies are chosen and the convergence to the desired formation and non-collision is analyzed for any number of robots. A decentralized formation strategy must comply with two fundamental requirements: Global convergence to the desired formation and inter-agent collision avoidance (Cao et al. (1997)). 6

Current medium access control mechanisms are based on collision avoidance and collided packets are discarded. The recent work on ZigZag decoding departs from this approach by recovering the original packets from multiple collisions. In this paper, we present an algebraic representation of collisions which allows us to view each collision as a linear combination of the original packets. The transmitted, colliding packets may themselves be a coded version of the original packets. We propose a new acknowledgment (ACK) mechanism for collisions based on the idea that if a set of packets collide, the receiver can afford to ACK exactly one of them and still decode all the packets eventually. We analytically compare delay performance of such collision recovery schemes with other collision avoidance approaches in the context of a single hop wireless erasure network. From the delay perspective, our scheme, without any coordination, outperforms not only ALOHA-type random access mechanisms, but also centralized scheduling.

This paper is focused on dynamic modeling and control system design as well as vision based collision avoidance for multi-rotor unmanned aerial vehicles (UAVs). Multi-rotor UAVs are defined as rotary-winged UAVs with multiple rotors. These multi-rotor UAVs can be utilized in various military situations such as surveillance and reconnaissance. They can also be used for obtaining visual information from steep terrains or disaster sites. In this paper, a quad-rotor model is introduced as well as its control system, which is designed based on a proportional-integral-derivative controller and vision-based collision avoidance control system. Additionally, in order for a UAV to navigate safely in areas such as buildings and offices with a number of obstacles, there must be a collision avoidance algorithm installed in the UAV's hardware, which should include the detection of obstacles, avoidance maneuvering, etc. In this paper, the optical flow method, one of the vision-based collision avoidance techniques, is introduced, and multi-rotor UAV's collision avoidance simulations are described in various virtual environments in order to demonstrate its avoidance performance.