Avoidance Control Research Articles

Deep reinforcement learning-based model-free path planning and collision avoidance for UAVs: A soft actor–critic with hindsight experience replay approach

In this paper, we propose a soft actor–critic (SAC) algorithm with hindsight experience replay (HER), called SACHER, which is a class of deep reinforcement learning (DRL) algorithm. SAC is an off-policy model-free DRL algorithm that outperforms earlier DRL algorithms in terms of exploration and robustness. However, in SAC, maximizing the entropy-augmented objective degrades the optimality of learning outcomes. We propose SACHER to improve the learning performance of SAC. We apply SACHER to the path planning and collision avoidance control of unmanned aerial vehicles (UAVs). We demonstrate the effectiveness of SACHER in terms of the success rate, learning speed, and collision avoidance performance of UAV operation.

Decentralized Robust Collision-Avoidance for Cooperative Multirobot Systems: A Gaussian Process-Based Control Barrier Function Approach

Data-based Machine Learning methods have been successfully applied to control system design in recent years. However, safety during the learning and control process is difficult to guarantee due to the inherent uncertainties. In this work, we propose a barrier function-based robust cooperative collision avoidance control framework for heterogeneous multirobot systems with model learning. First, a new control barrier function (CBF) design is proposed for cooperative collision avoidance, which leads to less conservativeness of the feasible control actions. Then, decentralized robust CBF conditions are derived which incorporate the estimation of the individual model uncertainty using Gaussian Process models such that each robot can guarantee safety with a high probability. Finally, a quadratic programming problem is formulated to obtain a controller which is minimally invasive to the nominal controller and satisfies the CBF and velocity constraints simultaneously. The decentralized implementation of the robust collision avoidance control strategy is explicitly shown and proven. Two simulation examples are given to demonstrate the effectiveness of the proposed control framework.

Obstacle avoidance control algorithm of self-driving electric vehicle based on DRL

Facing the increasingly severe pressure of environmental pollution, road safety and traffic congestion, intelligent vehicle has become the development focus of modern automobile industry, and it is also the main direction and key competitive field of automobile technology development in the future. This trend puts forward higher requirements for vehicle control system. Under the background of the vigorous development of electric vehicle and automatic driving technology, through the overall planning of obstacle avoidance strategy of automatic driving electric vehicle, studying the correct control method and designing obstacle avoidance system under different working conditions, it has theoretical guiding significance and practical application value for the development of obstacle avoidance control system of automatic driving electric vehicle in the future. This chapter first introduces the basic theoretical knowledge of reinforcement learning, then introduces the DL theory and classical neural network, and finally introduces DQN and DDPG algorithms in DRL, so as to interact RL data. Combining DL with reinforcement learning, the feature representation of complex driving scene is established, which is used as input to train intelligent vehicle obstacle avoidance control strategies that can complete various driving tasks, and transplanted to practical applications, so that they have better performance in automatic driving obstacle avoidance control. To sum up, DRL has great research and application value for obstacle avoidance control of self-driving electric vehicles, which can greatly promote the level of intelligent transportation system.

EF-TTOA: Development of a UAV Path Planner and Obstacle Avoidance Control Framework for Static and Moving Obstacles

With the increasing applications of unmanned aerial vehicles (UAVs) in surveying, mapping, rescue, etc., the security of autonomous flight in complex environments becomes a crucial issue. Deploying autonomous UAVs in complex environments typically requires them to have accurate dynamic obstacle perception, such as the detection of birds and other flying vehicles at high altitudes, as well as humans and ground vehicles at low altitudes or indoors. This work’s primary goal is to cope with both static and moving obstacles in the environment by developing a new framework for UAV planning and control. Firstly, the point clouds acquired from the depth camera are divided into dynamic and static points, and then the velocity of the point cloud clusters is estimated. The static point cloud is used as the input for the local mapping. Path finding is simplified by identifying key points among static points. Secondly, the design of a trajectory tracking and obstacle avoidance controller based on the control barrier function guarantees security for moving and static obstacles. The path-finding module can stably search for the shortest path, and the controller can deal with moving obstacles with high-frequency. Therefore, the UAV can deal with both long-term planning and immediate emergencies. The framework proposed in this work enables a UAV to operate in a wider field, with better security and real-time performance.

Chemical emasculation in cowpea (Vigna unguiculata (L.) Walp.) and dicotyledonous model species using trifluoromethanesulfonamide (TFMSA)

Hybridization plays an indispensable role in creating the diversity associated with plant evolution and genetic improvement of crops. Production of hybrids requires control of pollination and avoidance of self-pollination for species that are predominantly autogamous. Hand emasculation, male sterility genes or male gametocides have been used in several plant species to induce pollen sterility. However, in cowpea (Vigna unguiculata (L.) Walp), a self-pollinated cleistogamous dryland crop, only hand emasculation is used, but it is tedious and time-consuming. In this study, male sterility was effectively induced in cowpea and two dicotyledonous model species (Arabidopsis thaliana (L.) Heynh. and Nicotiana benthamiana Domin) using trifluoromethanesulfonamide (TFMSA). Pollen viability assays using Alexander staining showed that 30 ml of 1000 mg/l TFMSA with two-time treatments of one-week interval at the early stage of the reproductive phase under field or greenhouse conditions induced 99% pollen sterility in cowpea. TFMSA treatment induced non-functional pollen in diploid A. thaliana at two-time treatment of 10 ml of 125–250 mg/l per plant and N. benthamiana at two-time treatment of 10 ml of 250–1000 mg/l per plant. TFMSA-treated cowpea plants produced hybrid seeds when used as the female parent in crosses with non-treated plants used as male parents, suggesting that TFMSA had no effect on female functionality in cowpea. The ease of TFMSA treatment and its effectiveness to induce pollen sterility in a wide range of cowpea genotypes, and in the two model plant species tested in this study, may expand the scope of techniques for rapid pollination control in self-pollinated species, with potential applications in plant breeding and plant reproduction science.

Distributed dynamic matrix control with constrained optimization for collision and obstacle avoidance of simulated multiple quadcopters

AbstractA system of fast moving quadcopters has a high risk of collisions with neighboring quadcopters or obstacles. The objective of this work is to develop a control strategy for collision and obstacle avoidance of multiple quadcopters. In this paper, the problem of distributed dynamic matrix control (DMC) for collision avoidance among a team of multiple quadcopters attempting to reach consensus in the horizontal plane and yaw direction ( , and ) is investigated. Violations of a predetermined safety radius generates output constraints on the DMC optimization function, which has not been dealt with in the literature. Different from past works, the proposed strategy can perform collision avoidance in the , , and ‐directions. In addition, logarithmic barrier functions are implemented as input rate constraints on the control actions. Extensive simulation studies for a team of quadcopters illustrate promising results of the proposed control strategy and case variations. In addition, DMC parameter effects on the system performance are studied, and a successful study for obstacle avoidance is presented.

Simulation and experiment on obstacle avoidance control of concrete pump truck boom based on improved danger field and gradient projection method

Aiming at the shortcomings of the traditional robot obstacle avoidance algorithm applied directly to the leader–follower task transformation of concrete pump truck boom, an algorithm combined with improved danger field and improved gradient projection method for obstacle avoidance control of the boom is proposed. In the method, a joint limit avoidance function is used to avoid the angle overrun of the boom joints. And the danger field expression is modified to improve its engineering suitability. Moreover, a smoothing adjustment factor is introduced to improve the smoothness of the leader–follower task transformation of the boom. The influence of key control parameters on the safety and accuracy of boom movement is discussed through the simulation, and the reasonable ranges of the parameters are given. Furthermore, experiments are carried out to verify the effectiveness of the algorithm. The method provides a solution for obstacle avoidance control of construction machinery with multijoint series boom.

Lane-Change Collision Avoidance Control for Automated Vehicles with Control Barrier Functions

Lane-Change Collision Avoidance Control for Automated Vehicles with Control Barrier Functions

Enhanced multi-agent systems formation and obstacle avoidance (EMAFOA) control algorithm

Most of the multi-agent formation and obstacle avoidance algorithms in the literature are computationally expensive and/or presents an ad hoc method for a specific type of systems. A general inexpensive, in term of computational complexity, multi-agent formation and obstacle avoidance algorithm is modeled and designed in this paper. The method builds on the leader-follower strategy for the simplicity and applicability for a wide range of the engineering systems. A novel artificial potential function (APF) is proposed. The proposed function has unique attributes which differentiate it superior to what is reported in the literature. The proposed algorithm can be applied for first order systems, second order systems, and non-holonomic systems. Also, the proposed method is free of local minima problem and oscillations. In addition, a novel multi-agent system formation control design is proposed in this work. The proposed design allows to embed any formation in the system paradigm and reduces complexity. Moreover, the stability of the proposed method is investigated in terms of Riccati equation and Lyapunov method. Furthermore, to show the effectiveness of the proposed method it applied and simulated for a second order leader and one follower system with specific formation. Then, a five second order agents with leader in a circular formation avoiding simple and complex obstacles are also introduced with different scenarios. Finally, twenty agents with square formation with two obstacles are simulated and investigated.

A Novel Obstacle Avoidance Consensus Control for Multi-AUV Formation System

In this paper, the fixed-time event-triggered obstacle avoidance consensus control for a multi-AUV time-varying formation system in a 3D environment is presented by using an improved artificial potential field and leader-follower strategy (IAPF-LF). Firstly, the proposed fixed-time control can achieve the desired multi-AUV formation within a fixed settling time in any initial system state. Secondly, an event-triggered communication strategy is developed to govern the communication among AUVs, and the communication energy consumption can be decremented. The time-varying formation obstacle avoidance control algorithm based on IAPF-LF is designed to avoid static and dynamic obstacles, the desired formation is maintained in the presence of external disturbances, and there is no Zeno behavior under the fixed-time event-triggered consensus control strategy. The stability of the system is proved by the Lyapunov function and inequality scaling. Finally, simulation examples and water pool experiments are reported to verify the performance of the proposed theoretical algorithms.

Automatic Emergency Collision Avoidance of Straight-Crossing Intelligent Vehicle at a 90-Degree Intersection Based on Vehicle-to-Everything Technology

<div>In order to reduce collision at a 90-degree intersection, an automatic emergency collision avoidance control method for intelligent vehicles based on vehicle-to-everything (V2X) technology is proposed. Most of the existing automatic emergency braking (AEB) control algorithms are designed for a single high-friction road with reference to the European New Car Assessment Programme (Euro NCAP) evaluation procedures, and they do not consider changes in road friction. Thus, it may be difficult to avoid collision successfully on a low-friction road. Although some studies have considered the variation of road friction, they are only applicable to straight-line rear-end collisions and cannot be directly applied to intersections. In addition, most studies regard the vehicle only as a particle, ignoring the actual dynamic characteristics of the vehicle. The main contribution of this article is to present an AEB control strategy by V2X technology, which can make the intelligent vehicle avoid collisions at a 90-degree intersection effectively. The proposed time-to-collision (TTC) adaptive algorithm has considered various road surfaces, and its effectiveness is verified by the co-simulation of Matlab/Simulink, CarSim, and Prescan on a typical urban intersection road.</div>

Obstacle Avoidance Based on Stereo Vision Navigation System for Omni-directional Robot

This paper addresses the problem of obstacle avoidance in mobile robot navigation systems. The navigation system is considered very important because the robot must be able to be controlled from its initial position to its destination without experiencing a collision. The robot must be able to avoid obstacles and arrive at its destination. Several previous studies have focused more on predetermined stationary obstacles. This has resulted in research results being difficult to apply in real environmental conditions, whereas in real conditions, obstacles can be stationary or moving caused by changes in the walking environment. The objective of this study is to address the robot’s navigation behaviors to avoid obstacles. In dealing with complex problems as previously described, a control system is designed using Neuro-Fuzzy so that the robot can avoid obstacles when the robot moves toward the destination. This paper uses ANFIS for obstacle avoidance control. The learning model used is offline learning. Mapping the input and output data is used in the initial step. Then the data is trained to produce a very small error. To support the movement of the robot so that it is more flexible and smoother in avoiding obstacles and can identify objects in real-time, a three wheels omnidirectional robot is used equipped with a stereo vision sensor. The contribution is to advance state of the art in obstacle avoidance for robot navigation systems by exploiting ANFIS with target-and-obstacles detection based on stereo vision sensors. This study tested the proposed control method by using 15 experiments with different obstacle setup positions. These scenarios were chosen to test the ability to avoid moving obstacles that may come from the front, the right, or the left of the robot. The robot moved to the left or right of the obstacles depending on the given Vy speed. After several tests with different obstacle positions, the robot managed to avoid the obstacle when the obstacle distance ranged from 173 – 150 cm with an average speed of Vy 274 mm/s. In the process of avoiding obstacles, the robot still calculates the direction in which the robot is facing the target until the target angle is 0.

Research on Obstacle Avoidance Control of Multiple UAV Formation based on Genetic Algorithm

The UAV (Unmanned Aerial Vehicle) group cooperative formation flight technology has the advantages of wide coverage, large activity radius, strong overall search ability and high efficiency of the aircraft group. Therefore, it is suitable for various complex tasks in the military field such as battlefield environment reconnaissance, tactical attack and cooperative search. This paper proposes a consistency control strategy based on GA (Genetic Algorithm) and applies it to multi-UAV formation obstacle avoidance, which can effectively solve the collision between UAVs and between UAV formation and obstacles. Demodulate the received ground desired control command, and introduce an additional auxiliary traction acceleration through GA to avoid the local optimal solution. The auxiliary traction acceleration is related to the speed and relative position of UAV and obstacles. It can be used as a disturbance to solve the local optimal solution, and also as an auxiliary acceleration to improve the speed of avoiding moving obstacles. Finally, the rapid formation and obstacle avoidance of UAV fleet during flight are realized, and the survivability of the fleet in the battlefield environment is improved.

Integrated Decision Making and Motion Control for Autonomous Emergency Avoidance Based on Driving Primitives Transition

Emergency avoidance is an aggressive maneuver with high collision risk. This paper presents an integrated decision making and motion control framework to achieve emergency avoidance in complex driving scenarios. This is realized by combining reasonable decision making based on driving primitives transition and efficient motion control under critical driving conditions. For decision making, the driving primitives including braking, lane changing, and accelerating are generalized to perform a complete emergency avoidance maneuver through the Minimum Safety Spacing analysis, which is numerically executed as a mapping function of the host vehicle's speed and road adhesion coefficient. For motion control, the quintic polynomial-based path planning is formulated as solving a minimum lane changing duration problem. Moreover, the Linear Time-Varying Model Predictive Control combined with the Direct Yaw-moment Control is put forward to realize accurate path tracking control for emergency avoidance. The effectiveness of the proposed scheme is examined under various scenarios based on comprehensive Hardware-in-Loop tests. The results show that the proposed framework can realize timely emergency avoidance with guaranteed vehicle dynamics stability based on proper decision-making and accurate path tracking control.

Path Planning and Obstacle Avoidance Control for Autonomous Multi-Axis Distributed Vehicle Based on Dynamic Constraints

Obstacle avoidance problem for the autonomous vehicle has received more and more attention these years, especially for the autonomous heavy vehicle, which has the high gravity center, large carrying capacity and promising commercial prospect. However, the vehicle dynamic properties have been rarely considered for path planning, which is a crucial factor for driving safety. An integrated collision avoidance framework that consists of a new path planner and a tracking controller considering multiple dynamic constraints is proposed for an autonomous multi-axis distributed vehicle. In the upper level, a new optimal path generator based on the B-splines is designed for safety and stability purposes, and the collision avoidance path is optimized considering multiple dynamic constraints, including the tire nonlinear dynamic, lateral stability limits and the anti-slip constraints. Meanwhile, a safety assessment evaluator according to the time to collision calculation is designed for risk level recognition and path planning weight determination. In the lower level, a path tracking controller based on the nonlinear model predictive control (NMPC) is designed to improve the control accuracy, and a high-fidelity nonlinear dynamic predictive vehicle model with 16 degrees of freedom is established to depict the vehicle dynamic properties comprehensively. To solve the nonlinear optimization problem and get the optimal control steering angle output, an adaptive weight adjustment strategy and a varying predictive duration method are formulated. The optimization constraints related to steering actuator ability, plane stability limits, rollover prevention thresholds and tire adhesion requirements are constructed and converted as the bounds of the vehicle dynamic states. To verify the proposed framework, the simulation and HIL test platform are built and different driving scenarios are validated. The test results show the satisfactory performance of path planning and path tracking considering the dynamic constraints for safety and stability

Event-triggered distributed robust optimal control of nonholonomic mobile agents with obstacle avoidance formation, input constraints and external disturbances

This paper proposes an event-triggered distributed robust optimal control algorithm for nonholonomic mobile agents (NMA) systems with collision avoidance, asymmetrically saturated inputs and external disturbances. By employing the limit cycle principle and developing the adaptive dynamic programming, zero-sum game theory, and an event-triggering mechanism, the algorithm can optimize an H∞ cost function and relax both the perfect velocity tracking assumption and the persistent excitation condition. First, the graph theory is used to establish the communication configuration, followed by the introduction of the distributed kinematic control for collision avoidance. Second, as a perfect velocity tracking assumption cannot be guaranteed under dynamics changes, input constraints and external disturbances, the distributed optimal robust control algorithm is designed. Third, by developing a new event-triggering mechanism, the burden of computational complexity and communications is reduced. The closed-loop stability and the zeno-behavior exclusion are proven by the Lyapunov theory. Finally, a numerical simulation is conducted with comparison to the sampling period–based control algorithm to demonstrate the effectiveness of the proposed algorithm.

Experimental study on autonomous assembly of multiple spacecraft simulators in a spinning scenario

Utilizing the autonomous rendezvous and docking among multiple spacecraft to construct a large space structure is a prospective on-orbit autonomous assembly mission. This paper presents a planar air-bearing experiment on the autonomous assembly of two chaser spacecraft simulators and one spinning target spacecraft simulator. The mission process includes four distinct phases. While the first two phases use the real-time assembly and collision avoidance controllers proposed, the assembly control laws with analytical expressions play its role in the remaining phases. Both neighboring spacecraft simulators and external object serve as the obstacles during the design process. The hardware-in-the-loop experimental system consists of three spacecraft simulators with electromagnetic docking mechanism installed, a granite testbed, a motion tracking system and a wireless transmission system. The experimental results show that the proposed multistage control strategy can successfully realize the autonomous collision-free assembly of three spacecraft simulators in the spinning scenario.

A high-speed human-like collision avoidance controller based on a neural network under different road adhesion coefficients

Safety and stability have been two main considerations in the field of collision avoidance. However, if the response of a vehicle to avoid collision does not conform to the habits of a human driver, it can cause tension and discomfort to the driver, or even worse, misunderstanding between the driver and an automatic driving system can occur, leading to a traffic accident. Therefore, a driver’s reaction characteristics should be considered, and the reaction expected by the driver should be satisfied as much as possible. This study proposes a human-like collision avoidance model based on a neural network under emergency conditions. The vehicle response data collected from experienced drivers in the collision-avoidance stage via driving simulators are used to train the neural network model. A front-wheel angle controller is developed to track the output of the human-like neural network model. Moreover, the stability region of a vehicle is obtained by the K-means method. Further, a differential braking controller is designed to ensure the safety and stability of the vehicle. The simulation results show that the proposed human-like collision avoidance controller not only meets the safety and stability requirements of collision avoidance but can also ensure good driving comfort for human drivers.

Disruption event characterization and forecasting in tokamaks

Disruption prediction and avoidance is a critical need for next-step tokamaks, such as ITER. Disruption Event Characterization and Forecasting (DECAF) research fully automates analysis of tokamak data to determine chains of events that lead to disruptions and to forecast their evolution allowing sufficient time for mitigation or complete avoidance of the disruption. Disruption event chains related to local rotating or global magnetohydrodynamic (MHD) modes and vertical instability are examined with warnings issued for many off-normal physics events, including density limits, plasma dynamics, confinement transitions, and profile variations. Along with Greenwald density limit evaluation, a local radiative island power balance theory is evaluated and compared to the observation of island growth. Automated decomposition and analysis of rotating tearing modes produce physical event chains leading to disruptions. A total MHD state warning model comprised of 15 separate criteria produces a disruption forecast about 180 ms before a standard locked mode detector warning. Single DECAF event analyses have begun on KSTAR, MAST, and NSTX/-U databases with thousands of shot seconds of device operation using from 0.5 to 1 × 106 tested sample times per device. An initial multi-device database comparison illustrates a highly important result that plasma disruptivity does not need to increase as βN increases. Global MHD instabilities, such as resistive wall modes (RWMs), can give the briefest time period of warning before disruption compared to other physics events. In an NSTX database with unstable RWMs, the mode onset, loss of boundary and current control, and disruption event warnings are found in all cases and vertical displacement events are found in 91% of cases. An initial time-dependent reduced physics model of kinetic RWM stabilization created to forecast the disruption chain predicts instability 84% of the time for experimentally unstable cases with a relatively low false positive rate. Instances of the disruption event chain analysis illustrate dynamics including H–L back transitions for rotating MHD and global RWM triggering events. Disruption warnings are issued with sufficient time before the disruption (on transport timescales) to potentially allow active profile control for disruption avoidance, active mode control, or mitigation.

Time Optimal Trajectory Generation with Obstacle Avoidance by Using Optimal Control Theory for a Wheeled Mobile Robot

The design of the mobile robot path is important when obstacles are present in the environment. In the present study, the theory of optimal control for path design and obstacle avoidance via simultaneous minimization of the time and kinetic energy is proposed. Nonlinear equations of robot motion without simplification are considered in optimum control problems, and in order to prevent collisions, the potential functions are utilized. In the next phase, the cost function is proposed that includes velocity inputs, time, and the potential function for obstacle avoidance, in which the nonlinear equation of the motion of the mobile robot is deemed as a constraint. The final equations are numerically solved, and the capability and effectiveness of the presented method will be presented via different simulations on the mobile robot.