Algorithm For Autonomous Vehicles Research Articles

Two-Level MPC Speed Profile Optimization of Autonomous Electric Vehicles Considering Detailed Internal and External Losses

This paper proposes a novel two-level model predictive control (MPC) speed control algorithm for autonomous vehicles as a successive convex optimization problem focused on both energy use and arrival time. Internal losses such as detailed motor/inverter efficiency and battery loss, as well as external losses, such as wind and grade, are considered. The effect of the higher accessory energy usage of autonomous vehicles on the energy-optimal speed profile is considered in the algorithm and investigated in the paper. The proposed successive convex approach produces a highly accurate optimal speed profile while also being solvable in real-time with the vehicle on-board computing resources. An electric vehicle model is created in MATLAB/Simulink and validated to real-world logged driving data. This vehicle model is used to perform a variety of simulated test cases, which show an energy savings potential of about 1% to 20% for different driving conditions, compared to a non-energy-optimal driving profile.

A Novel Pure Pursuit Algorithm for Autonomous Vehicles Based on Salp Swarm Algorithm and Velocity Controller

Pure pursuit algorithm is one of the most effective ways of path tracking in autonomous vehicles. Nevertheless, the tracking accuracy of the existing pure pursuit algorithm is limited by the look-ahead distance. In this paper, to improve the tracking accuracy of the pure pursuit algorithm, a novel pure pursuit algorithm based on the optimized look-ahead distance named OLDPPA is proposed. Four improvements are presented in OLDPPA. Firstly, to find a better look-ahead distance of pure pursuit algorithm, salp swarm algorithm (SSA) is used in pure pursuit algorithm. Secondly, Brownian motion, a random motion mechanism of particles, is introduced in SSA to enhance its exploitation and exploration capabilities. Thirdly, to accelerate the convergence speed of SSA, a weighted mechanism which uses two different weights in the search process to adjust the salps closer to the food source quickly is assigned. Based on innovations 2 and 3, adaptive Brownian motion salp swarm algorithm (ABMSSA) is proposed and applied to pure pursuit algorithm. Finally, a velocity controller which outputs the speed of the next moment according to the distance and time interval between the look-ahead point and the current vehicle position is designed in OLDPPA, to ensure that the vehicle reaches its destination at a specified time. To verify the effectiveness and efficiency of OLDPPA, OLDPPA is applied in four different paths and the corresponding results are compared with other pure pursuit algorithms that use different look-ahead distances. Experimental results show that the tracking accuracy of OLDPPA is better than other algorithms.

Virtual Target-Based Overtaking Decision, Motion Planning, and Control of Autonomous Vehicles

This paper describes the design, implementation, and evaluation of a virtual target-based overtaking decision, motion planning, and control algorithm for autonomous vehicles. Both driver acceptance and safety, when surrounded by other vehicles, must be considered during autonomous overtaking. These are considered through safe distance based on human driving behavior. Since all vehicles cannot be equipped with a vehicle to vehicle communications at present, autonomous vehicles should perceive the surrounding environment based on local sensors. In this paper, virtual targets are devised to cope with the limitation of cognitive range. A probabilistic prediction is adopted to enhance safety, given the potential behavior of surrounding vehicles. Then, decision-making and motion planning has been designed based on the probabilistic prediction-based safe distance, which could achieve safety performance without a heavy computational burden. The algorithm has considered the decision rules that drivers use when overtaking. For this purpose, concepts of target space, demand, and possibility for lane change are devised. In this paper, three driving modes are developed for active overtaking. The desired driving mode is decided for safe and efficient overtaking. To obtain desired states and constraints, intuitive motion planning is conducted. A stochastic model predictive control has been adopted to determine vehicle control inputs. The proposed autonomous overtaking algorithm has been evaluated through simulation, which reveals the effectiveness of virtual targets. Also, the proposed algorithm has been successfully implemented on an autonomous vehicle and evaluated via real-world driving tests. Safe and comfortable overtaking driving has been demonstrated using a test vehicle.

A Novel Congestion Avoidance Algorithm for Autonomous Vehicles Assessed by Queue Modeling

Autonomous vehicle (AV) fleet management is one of the major aspects of AV development that needs to be standardized before AV deployment. There has been no consensus on whether AV deployment in general will be beneficial or detrimental in terms of road congestion. There are similarities between packet transmission in computer networks and AV transportation in road networks. In this work, the authors argue that congestion avoidance algorithms used in computer networks can be applied for AV fleet management. Authors modify and evaluate a novel adaptation of additive increase and multiplicative decrease (AMID) congestion avoidance algorithm. The authors propose assigning different priorities to transportation tasks in order to facilitate sharing the limited resources in such as usage of the road network. This will be modeled and assessed using a queueing model based on AVs arrival distribution. This will result in a load balancing paradigm that can be used to share and manage limited resources. Then, by using numerical study authors merge congestion avoidance and load balancing to analyze the authors' scheme in term of road network throughput (number of cars in network for a given time) for AV fleet management. Their evaluation demonstrates the improvement in terms of road network throughput.

Road surface estimation based LPV control design for autonomous vehicles

The paper proposes a new road surface estimation algorithm for autonomous vehicles using a machine-learning based method, which is in cooperation with the lateral control of the vehicle. The algorithm uses large datasets, which can be collected e.g. from the on-board sensors of the vehicle, or it also can be provided by vehicle dynamic simulation softwares. The result of the surface estimation is built-in the lateral control system as a scheduling parameter. Furthermore, the lateral control design is based on the Linear Parameter Varying (LPV) method, which guarantees the safe motion of the vehicle against varying parameters of the system. Finally, a comprehensive simulation is presented to show the efficiency and the operation of the proposed control system.

A 3D LiDAR Data-Based Dedicated Road Boundary Detection Algorithm for Autonomous Vehicles

Effectively detecting road boundaries in real time is critical to the applications of autonomous vehicles, such as vehicle localization, path planning, and environmental understanding. To precisely extract the irregular road boundaries or those blocked by obstructions on the road from the 3D LiDAR data, a dedicated algorithm consisting of four steps is proposed in this paper. The steps are as follows. First, the 3D LiDAR data is pre-processed, employing the vehicle position and attitude information, and many noise points are deleted. Second, the ground points are quickly separated from the pre-processed point cloud data to reduce the disturbance from the obstacles on the road; this greatly decreases the size of the points cloud to be processed. Third, the candidate points of the road boundaries are searched along the predicted trajectory of the autonomous vehicle and filtered using the unique features of the boundary points. Last, a spline fit model is applied to smoothen the road boundaries. An experiment to test the performance of the proposed algorithm was conducted on the “Xinda” autonomous vehicle under various road scenarios. The experimental results show that the average accuracy of the proposed algorithm exceeds 93%, and its average processing time is approximately 36.5 ms/frame, which outperforms most of the state-of-the-art methods. This indicates that the proposed algorithm can robustly extract the road boundary in real time even if there are many obstacles on the road. This algorithm has been tested on “Xinda” autonomous vehicle for over 1000 kilometers, and its performance was always stable.

Safe and Ecological Speed Profile Planning Algorithm for Autonomous Vehicles Using a Parametric Multiobjective Optimization Procedure

This paper proposes and evaluates an algorithm called Multi-Objective planning based on Simulated Annealing (MOSA) that plans a trajectory (speed profile) for a passenger car on a free, single lane road. This algorithm is relying on a decomposition of the decision space into “chunks” that are optimized separately. Two objectives have been taken into account: travel time and fuel consumption. Optimization constraints are built from safety modelings combining legal speed, curves speed limits and junctions limits. The multi-objective optimization is performed through a linear scalairisation method and the optimization is a parametric optimization based on simulated annealing. The algorithm has been tested on simulated annealing convergence and results show a good convergence under 500 iterations and a small sensitivity to variables initialization. However, sensitivity to core parameters of the simulated annealing (initial temperature and temperature decreasing rate) is very high and some guidelines for the calibration of these parameters are given in this paper. Then, the algorithm has been tested and compared to experimental results and it shows that, even if some drivers can drive the road quicker than the algorithm, they cannot drive with a lower fuel consumption. Furthermore, the algorithm results are better than the most of the experimental results according to the Pareto definition of dominance and global results outperform results from another planning algorithm based on Dijkstra’s algorithm. Future works will concentrate on improving the algorithm to be more reactive to unexpected obstacles and more consistant in the “chunks” transitions.

New road anomaly detection and characterization algorithm for autonomous vehicles

This paper presents a new algorithm for detecting and characterizing potholes and bumps directly from noisy signals acquired using an Accelerometer. A wavelet transformation based filter was used to decompose the signals into multiple scales. These coefficients were correlated across adjacent scales and filtered using a spatial filter. Road anomalies were then detected based on a fixed threshold system, while characterization was achieved using unique features extracted from the filtered wavelet coefficients. Our analyses show that the proposed algorithm detects and characterizes road anomalies with high levels of accuracy, precision and low false alarm rates.

Functional perspective-based probabilistic fault detection and diagnostic algorithm for autonomous vehicle using longitudinal kinematic model

This paper describes a functional perspective-based probabilistic fault detection and diagnostic algorithm of an autonomous vehicle using a longitudinal kinematic model. The relative displacement and velocity between the subject vehicle and a preceding vehicle was obtained by a radar installed in front of the autonomous vehicle. The obtained relative values were used to control the longitudinal behavior of the autonomous vehicle, the longitudinal acceleration of which was obtained from an internal sensor. In order to detect and diagnose actual faults in the obtained values, such as relative displacement, velocity, and acceleration, a fault detection and diagnostic algorithm for the longitudinal control of the autonomous vehicle was developed using a sliding mode observer and predictive function. The probabilistic analysis of fault signals was conducted using the constructed sliding mode observer and predictive function. The actual driving data of the vehicle preceding the subject vehicle was used for the rational performance evaluation of the proposed algorithm. The performance evaluation was conducted in the MATLAB/SIMULINK environment. The evaluation results showed that the proposed fault detection and diagnostic algorithm can stochastically detect and diagnose applied fault signals.

Introducing Ethical Thinking About Autonomous Vehicles Into an AI Course

A computer science faculty member and a philosophy faculty member collaborated in the development of a one-week introduction to ethics which was integrated into a traditional AI course. The goals were to: (1) encourage students to think about the moral complexities involved in developing accident algorithms for autonomous vehicles, (2) identify what issues need to be addressed in order to develop a satisfactory solution to the moral issues surrounding these algorithms, and (3) and to offer students an example of how computer scientists and ethicists must work together to solve a complex technical and moral problems. The course module introduced Utilitarianism and engaged students in considering the classic "Trolley Problem," which has gained contemporary relevance with the emergence of autonomous vehicles. Students used this introduction to ethics in thinking through the implications of their final projects. Results from the module indicate that students gained some fluency with Utilitarianism, including a strong understanding of the Trolley Problem. This short paper argues for the need of providing students with instruction in ethics in AI course. Given the strong alignment between AI's decision-theoretic approaches and Utilitarianism, we highlight the difficulty of encouraging AI students to challenge these assumptions.

Study on Robust Lateral Controller for Differential GPS-Based Autonomous Vehicles

Recently, technological advancements in autonomous vehicle development have continued to accelerate. In this paper, we propose a lateral controller and navigation algorithm for autonomous vehicles based on the Differential Global Positioning System (DGPS), core technology of autonomous vehicles. In this study, an H-infinity (H∞) controller was designed lateral controller to ensure nominal safety and robustness against noise, external disturbances and structural and non-structural errors in vehicle modeling. Meanwhile, the “pure pursuit” approach which geometrically follows a path was employed as a path-tracking technique for the proposed navigation algorithm. A vehicle modeling simulation was conducted to evaluate the performance of the proposed method using a twodegrees- of-freedom linear model. The lateral H∞ controller and navigation algorithm were applied to an actual vehicle, Their performances were evaluated by comparing the path tracking error at various speeds of autonomous vehicles with that of the proportional-integral-derivative (PID) controller.

Optimal path planning for an autonomous articulated vehicle with two trailers

This paper proposed an optimal path planning algorithm for autonomous vehicle with two trailers in autonomous navigation. The proposed algorithm is based on combination of artificial potential field (APF) method and optimal control theory. A linear two-degree-of-freedom vehicle model with both lateral and yaw motion is derived and simulated in MATLAB environment. The optimal control theory is applied to generate an optimal free-obstacle path of the robotic vehicle from a starting point to the goal location. The obstacle-avoidance technique is mathematically modelled using a potential function based on the proposed sigmoid function. The constructed potential field model can achieve an accurate analytic description of objects in three dimensions. Moreover, the proposed model of potential field requires very modest computation at run time. The APF includes both the attractive (the target) and repulsive (the obstacles) potential fields that will control the steering angle of the vehicle so that it can reach to its target location. Several simulations are carried out to check the fidelity of the proposed technique. The illustrated results demonstrate the generated optimal path of autonomous vehicles with consideration of vehicle dynamics constraints, obstacle avoidance and collision free criteria in reaching the goal location.

Optimal path planning for an autonomous articulated vehicle with two trailers

This paper proposed an optimal path planning algorithm for autonomous vehicle with two trailers in autonomous navigation. The proposed algorithm is based on combination of artificial potential field (APF) method and optimal control theory. A linear two-degree-of-freedom vehicle model with both lateral and yaw motion is derived and simulated in MATLAB environment. The optimal control theory is applied to generate an optimal free-obstacle path of the robotic vehicle from a starting point to the goal location. The obstacle-avoidance technique is mathematically modelled using a potential function based on the proposed sigmoid function. The constructed potential field model can achieve an accurate analytic description of objects in three dimensions. Moreover, the proposed model of potential field requires very modest computation at run time. The APF includes both the attractive (the target) and repulsive (the obstacles) potential fields that will control the steering angle of the vehicle so that it can reach to its target location. Several simulations are carried out to check the fidelity of the proposed technique. The illustrated results demonstrate the generated optimal path of autonomous vehicles with consideration of vehicle dynamics constraints, obstacle avoidance and collision free criteria in reaching the goal location.

자율주행자동차의 윤리화의 과제와 전망

The intelligent information society demands significant changes in the legal system, and the commercialization of autonomous vehicles is the most influential phenomenon that suggests the need for such changes. Focused on ethical issues of autonomous vehicles, the study is to identify the task of ‘ethicalization of autonomous vehicles’ and to address its future prospects. An ethical problem arises when autonomous vehicles replace human being in the decision-making process regarding safety of human life. The ethical challenges, such as the ‘Trolley Problem,’ show that the science and technology should not be expected to take a neutral stance on values and ethics in human society. First, as a theoretical foundation, this paper gives a general overview of discourse in the field of robot ethics in three categories: i) ethical guidelines of robotics; ii) moral status of robots; iii) ethical treatment of robot(robot rights). The notions of ‘autonomy’ and ‘robot-being’ are crucial in analyzing the applicability of robot ethics to the case of autonomous vehicles. Furthermore, the methods to build and design an ethical robot can be utilized to program the ethical algorithms for autonomous vehicles, and their practicality and effectiveness are examined by solving the trolley problem. Moreover, the paper provides ethical evaluations of prioritized decision making during autonomous vehicle crashes. In ethically dilemmatic situations, a priority-based hierarchical structure may accompany the issues of discriminating functions and the action/inaction distinction. Finally, as a closing remark, this paper suggests future prospects of the ethicalization of autonomous vehicles.

A Rawlsian algorithm for autonomous vehicles

Autonomous vehicles must be programmed with procedures for dealing with trolley-style dilemmas where actions result in harm to either pedestrians or passengers. This paper outlines a Rawlsian algorithm as an alternative to the Utilitarian solution. The algorithm will gather the vehicle's estimation of probability of survival for each person in each action, then calculate which action a self-interested person would agree to if he or she were in an original bargaining position of fairness. I will employ Rawls' assumption that the Maximin procedure is what self-interested agents would use from an original position, and then show how the Maximin procedure can be operationalized to produce unique outputs over probabilities of survival.

Transient and steady-state rotation centre of vehicle dynamics

The effect of acceleration - variable forward velocity, have been investigated on the steady-state and transient responses of turning vehicles and the resulted path of motion of the vehicle. Comparing the two mentioned responses of the vehicle could be used to prove that there is a negligible difference between the steady-state and transient centre of rotation of the vehicle in engineering applications. Dynamics of a vehicle with a constant steer angle and variable forward velocity have been analysed and presented as the proof. It has been shown that it is possible to predict the dynamics of vehicles using their steady state responses within acceptable engineering approximations. More specifically, we determine the dynamic rotation centre of vehicles and compare them with steady-state values. The result would be essential to design autodriver algorithm for autonomous vehicles.

Real-time path planning algorithm for autonomous vehicles in unknown environments

Real-time path planning algorithm for autonomous vehicles in unknown environments

Real-time path planning algorithm for autonomous vehicles in unknown environments

In this paper, a method of dynamic path planning algorithm for autonomous vehicles in cluttered environments is presented. The proposed method is based on the D* Lite algorithm with a smoothing method and local optimisation to enhance its performance in cluttered environments. The Lowess smoothing method has useful properties for the path planning problem especially in complex environments which involve lots of corners or direction changes required to avoid dynamic obstacles. Cubic hermite spline interpolation is used to describe curvature continuous trajectories for autonomous vehicles. Knowing the start and goal position, a continuous smooth trajectory can be decided. Results of proposed method are shown in simulations and experiments. Trajectories are demonstrated in various environments with and without additional obstacles. Quantitative results are shown and analysed to validate the proposed method.

Extended Kalman Filter Based Path-Planning Algorithm for Autonomous Vehicles with I2V Communication

Abstract Path-planning algorithms that can circumvent moving obstacles are required for realizing reliable autonomous vehicles. This investigation presents a path-planning algorithm for autonomous vehicle (AV) that uses infrastructure-to-vehicle (I2V) communication, Extended Kalman Filter (EKF) and behaviour based hybrid controllers for circumventing moving obstacles. The I2V communication provides the measurements required for estimating the current vehicle position. Vehicle mounted sensors are used to ascertain the current obstacle position and the dynamical equations are used to predict the future obstacle position. The EKF then estimates the future position of the vehicle relative to the obstacles and uses a hybrid controller that switches among the possible control actions. Our results show that the EKF based path-planning algorithm is able to circumvent moving obstacles even with non-linear dynamics.

Cooperative Surface/Underwater Navigation for AUV Path following missions

Abstract: The paper presents acoustic navigation aiding and path following results from demonstration experiments in Lisbon, Portugal. The demonstration was carried out as part of the second year CADDY Review Meeting. The paper presents the concept of the underwater leader, which entails an underwater vehicle, performing a desired task, and a surface vehicle maintaining relative position to improve navigation aiding through acoustics. The surface controller, utilizing the artificial potential field method, is proposed as an alternative to classical tracking and positioning controllers. Even in presence of multiple agents, the controller offers a more relaxed tracking and positioning algorithm for autonomous vehicles. The acoustic data-exchange scheme, required to achieve situation awareness of all agents, is described to specify cycle times and delays that have to be taken into account during state estimation. Finally, results from public demonstrations are presented and analyzed both from the surface and underwater perspectives.