Obstacle Avoidance For Autonomous Vehicles Research Articles

Exact Obstacle Avoidance for Autonomous Vehicles in Polygonal Domains

Exact Obstacle Avoidance for Autonomous Vehicles in Polygonal Domains

Framework of Active Obstacle Avoidance for Autonomous Vehicle Based on Hybrid Soft Actor-Critic Algorithm

Framework of Active Obstacle Avoidance for Autonomous Vehicle Based on Hybrid Soft Actor-Critic Algorithm

Design of Obstacle Avoidance for Autonomous Vehicle Using Deep Q-Network and CARLA Simulator

In this paper, we propose a deep Q-network (DQN) method to develop an autonomous vehicle control system to achieve trajectory design and collision avoidance with regard to obstacles on the road in a virtual environment. The intention of this work is to simulate a case scenario and train the DQN algorithm in a virtual environment before testing it in a real scenario in order to ensure safety while reducing costs. The CARLA simulator is used to emulate the motion of the autonomous vehicle in a virtual environment, including an obstacle vehicle parked on the road while the autonomous vehicle drives on the road. The target position, real-time position, velocity, and LiDAR point cloud information are taken as inputs, while action settings such as acceleration, braking, and steering are taken as outputs. The actions are sent to the torque control in the transmission system of the vehicle. A reward function is created using continuous equations designed, especially for this case, in order to imitate human driving behaviors. The results demonstrate that the proposed method can be used to navigate to the destination without collision with the obstacle, through the use of braking and dodging methods. Furthermore, according to the trend of DQN behavior, a better result can be obtained with an increased number of training episodes. This method is a non-global path planning method successfully implemented on a virtual environment platform, which is an advantage of this method over other autonomous vehicle designs, allowing for simulation testing and application with further experiments in future work.

A Prototype of Obstacle Avoidance for Autonomous Vehicle

Obstacle avoidance is one of the major tasks needed to be carefully focused by the autonomous system designers. In this digital era, most industries are moving towards autonomous systems. Obstacle avoidance is considered as a primary concern for any autonomous system. In this paper, a prototype of an autonomous vehicle is presented, which is capable of obstacle avoidance using an ultrasonic sensor for its movement and avoidance. An Arduino microcontroller is used to achieve the desired operation. In order to achieve the desired task of the proposed system, a proper methodology is followed which combines appropriate selection of hardware components as well as logic design of actions for obstacle avoidance. The proposed system can easily detect an obstacle, and move accordingly towards the safe path, by first detecting and then verifying the safe path. This can be very useful if implemented in real life. It can ultimately reduce the chances of accidents of trains and road vehicles which will save lots of lives. It can also detect broken roads and train tracks, which may result in reducing the chances of accidents to some extent. The accuracy of the autonomous vehicle depends on the output received by the ultrasonic sensor; therefore, it is not affected by the lighting environment. The prototype has been tested in various experimental settings and achieves appropriate results.

RTOB SLAM: Real-Time Onboard Laser-Based Localization and Mapping

RTOB-SLAM is a new low-computation framework for real-time onboard simultaneous localization and mapping (SLAM) and obstacle avoidance for autonomous vehicles. A low-resolution 2D laser scanner is used and a small form-factor computer perform all computations onboard. The SLAM process is based on laser scan matching with the iterative closest point technique to estimate the vehicle’s current position by aligning the new scan with the map. This paper describes a new method which uses only a small subsample of the global map for scan matching, which improves the performance and allows for a map to adapt to a dynamic environment by partly forgetting the past. A detailed comparison between this method and current state-of-the-art SLAM frameworks is given, together with a methodology to choose the parameters of the RTOB-SLAM. The RTOB-SLAM has been implemented in ROS and perform well in various simulations and real experiments.

Development of an Improved Rapidly Exploring Random Trees Algorithm for Static Obstacle Avoidance in Autonomous Vehicles.

Safe path planning for obstacle avoidance in autonomous vehicles has been developed. Based on the Rapidly Exploring Random Trees (RRT) algorithm, an improved algorithm integrating path pruning, smoothing, and optimization with geometric collision detection is shown to improve planning efficiency. Path pruning, a prerequisite to path smoothing, is performed to remove the redundant points generated by the random trees for a new path, without colliding with the obstacles. Path smoothing is performed to modify the path so that it becomes continuously differentiable with curvature implementable by the vehicle. Optimization is performed to select a “near”-optimal path of the shortest distance among the feasible paths for motion efficiency. In the experimental verification, both a pure pursuit steering controller and a proportional–integral speed controller are applied to keep an autonomous vehicle tracking the planned path predicted by the improved RRT algorithm. It is shown that the vehicle can successfully track the path efficiently and reach the destination safely, with an average tracking control deviation of 5.2% of the vehicle width. The path planning is also applied to lane changes, and the average deviation from the lane during and after lane changes remains within 8.3% of the vehicle width.

Research on Active Obstacle Avoidance for Autonomous Vehicle Based on Model Predictive Control

In order to track the active obstacle avoidance path of the autonomous vehicle, this thesis proposes two controllers with different inputs and constraints, on the basis of the Model Predictive Control (MPC). The controller A takes front-wheel steering angle as control input, while the controller B adds rear-wheel braking torque as another control input with extra constraints on the rear wheel braking torque. The simulation results indicate that both controllers can well track the desired path. More specifically, the performance of controller B is better than controller A in terms of lateral displacement and yaw rate, but the performance of controller A is better in yaw angle.

Reference Path Generation and Obstacle Avoidance for Autonomous Vehicles Based on Waypoints, Dubins Curves and Virtual Force Field Method

In this study, reference path generation based on waypoints, Dubins curves and obstacle avoidance are focused. The motion of a wheeled robot vehicle is modeled by following the principles of point mass approach. While motion planning is performed, the importance of obtaining the shortest distance between two target points is illustrated. Dubins curves and waypoints are used to construct an optimum path generation strategy. Path planning algorithm developed is combined with an obstacle avoidance approach, known as the virtual force field method. The whole system was tested for different scenarios. In the first scenario, the path generation was tested for the case where obstacles, start and finish points of the reference path, and initial and final robot vehicle orientations were defined. In this case, waypoints were not specified. In the second scenario, the performance of the algorithm was tested for generating a complete reference path. Waypoints were specified and the shortest path between the start and end points of the desired path was generated. Successful results were obtained and presented in this paper.

Guidance Based Collision Free and Obstacle Avoidance of Autonomous Vehicles under Formation Constraints

This paper presents a nonlinear control design for contemporary formation coordination, obstacle avoidance and collision free of multiple autonomous vehicles. Within a leader-follower framework, the geometric formation is guaranteed by speed adaptation of individual path following control. Meanwhile, nonlinear global heading guidance deign is highlighted and augmented for obstacle avoidance and collision free. Simulation results with seven unicycle-type vehicles show the performance of the guidance based nonlinear control strategy.

Obstacle avoidance of autonomous vehicles based on model predictive control

This paper presents an obstacle avoidance scheme for autonomous vehicles as an active safety procedure in unknown environments. Safe trajectories are generated using the non-linear model predictive framework, in which the simplified dynamics of the vehicle are used to predict the state of the vehicle over the look-ahead horizon. To compensate for the slight dissimilarity between the simplified model and the actual vehicle, a separate controller is designed to track the generated trajectory. The longitudinal dynamics of the vehicle are controlled using the inverse dynamics of the vehicle powertrain model, and the lateral dynamics are controlled using a linear quadratic regulator. In the non-linear model predictive framework, to obtain safe trajectories, local obstacle information is incorporated into the performance index using a parallax-based method. Simulation results on a full non-linear vehicle model show that the proposed combination of model-predictive-control-based trajectory generation and tracking controller gives satisfactory online obstacle avoidance performance.

Two Sensor Based Obstacle Avoidance for Autonomous Vehicles

Individual sensor types have their limitations and advantages in certain environments. The focus of this paper is to detail with an application of two different sensor types on the same autonomous vehicle. Each sensor complements the other, allowing more robust obstacle avoidance algorithms to be implemented. The particular sensor types used in combination in this application are: (i) infrared diodes and phototransistor receivers; and (ii) ultrasonic transceivers.

A Comparison of Alternative Obstacle Avoidance Strategies for Vehicle Control

SUMMARY In Alleyne (1996) several vehicle control options were considered for Unintended Roadway Departure (URD) prevention and conclusions were drawn as to the efficacy of each method. This companion paper investigates the use of several different inputs for the control of a vehicle, in the context of Obstacle Avoidance for autonomous vehicles. In this investigation, the goal of the controller is to provide an intervention in the event of the vehicle detecting an obstacle in its path. The five types of inputs that will be considered are (i) Four Wheel Steering; (ii) Front Wheel Steering; (iii) Four Wheel Brake Steering; (iv) Front Wheel Brake Steering; and (v) Rear Wheel Brake Steering. The controller design is an LQ controller based on the simplified dynamics of a 2 degree of freedom bicycle model. However, the analysis of the different strategies are performed on a more complete, nonlinear vehicle model. A key contribution of this paper is the quantitative evaluation of the relative efficiencies of each of these input strategies being examined. Unlike most control schemes, an important metric of performance is the ratio of peak tire force used versus available tire force. The conclusions reached in this paper shed additional light on appropriate input actuator methods for vehicle guidance and control.