1
|
Vilaça Carrasco A, Silva Sequeira J. Tuning path tracking controllers for autonomous cars using reinforcement learning. PeerJ Comput Sci 2023; 9:e1550. [PMID: 38077605 PMCID: PMC10702720 DOI: 10.7717/peerj-cs.1550] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2023] [Accepted: 08/02/2023] [Indexed: 10/16/2024]
Abstract
This article proposes an adaptable path tracking control system, based on reinforcement learning (RL), for autonomous cars. A four-parameter controller shapes the behaviour of the vehicle to navigate lane changes and roundabouts. The tuning of the tracker uses an 'educated' Q-Learning algorithm to minimize the lateral and steering trajectory errors, this being a key contribution of this article. The CARLA (CAR Learning to Act) simulator was used both for training and testing. The results show the vehicle is able to adapt its behaviour to the different types of reference trajectories, navigating safely with low tracking errors. The use of a robot operating system (ROS) bridge between CARLA and the tracker (i) results in a realistic system, and (ii) simplifies the replacement of CARLA by a real vehicle, as in a hardware-in-the-loop system. Another contribution of this article is the framework for the dependability of the overall architecture based on stability results of non-smooth systems, presented at the end of this article.
Collapse
|
2
|
Wang J, Fader MTH, Marshall JA. Learning‐based model predictive control for improved mobile robot path following using Gaussian processes and feedback linearization. J FIELD ROBOT 2023. [DOI: 10.1002/rob.22165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/20/2023]
Affiliation(s)
- Jie Wang
- Ingenuity Labs Research Institute & Department of Electrical and Computer Engineering Queen's University Kingston Ontario Canada
| | - Michael T. H. Fader
- Ingenuity Labs Research Institute & Department of Electrical and Computer Engineering Queen's University Kingston Ontario Canada
| | - Joshua A. Marshall
- Ingenuity Labs Research Institute & Department of Electrical and Computer Engineering Queen's University Kingston Ontario Canada
| |
Collapse
|
3
|
Hung N, Rego F, Quintas J, Cruz J, Jacinto M, Souto D, Potes A, Sebastiao L, Pascoal A. A review of path following control strategies for autonomous robotic vehicles: Theory, simulations, and experiments. J FIELD ROBOT 2022. [DOI: 10.1002/rob.22142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Affiliation(s)
- Nguyen Hung
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Francisco Rego
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Joao Quintas
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Joao Cruz
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Marcelo Jacinto
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - David Souto
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Andre Potes
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Luis Sebastiao
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| | - Antonio Pascoal
- Department of Electrical and Computer Engineering, Institute for Systems and Robotics (ISR), Instituto Superior Técnico (IST) University of Lisbon Lisbon Portugal
| |
Collapse
|
4
|
Distributed Intelligent Learning and Decision Model Based on Logic Predictive Control. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:6431776. [PMID: 36082343 PMCID: PMC9448558 DOI: 10.1155/2022/6431776] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Revised: 07/18/2022] [Accepted: 07/25/2022] [Indexed: 12/02/2022]
Abstract
By the method of documentation and logical analysis, based on the data, based on logic and based on the knowledge of three kinds of artificial intelligence in the sports education, the intelligent learning system feedback delay are studied, combined with mobile communication which led to the artificial intelligence online sports games teaching, pattern recognition, and virtual technology combined with innovative teaching interaction and experience. Promoting the development of green PE teaching machine learning can identify the types of PE activities and realize efficient PE learning diagnosis. Intelligent decision support system can identify sports talents and improve the effect of personalized PE teaching evaluation. From the perspective of psychological development and education, the key problems to be solved in the integration of artificial intelligence and physical education are examined. Then, the consistent model predictive control for feedback delay of nonlinear sports learning multiagent system with network induced delay and random communication protocol is studied. Under the communication waiting mechanism designed, each agent has a certain tolerance of delay, and this tolerance can be determined by ensuring the stability of the system. At the same time, a random communication protocol is designed to ensure the ordered communication of the multiagent system. Finally, the effectiveness of the proposed algorithm is verified by numerical simulation. To solve the channel competition access problem of the sports intelligent learning system with special structure feedback delay model predictive control, a dual channel awareness scheduling strategy under the model predictive control framework was proposed, and the distributed threshold strategy of sensors and the priority threshold strategy of controllers were designed. It is proved that the sensor will eventually work at Nash equilibrium point under the policy updating mechanism, and the priority threshold strategy of the controller is better than the traditional independent and identically distributed access strategy. By avoiding the data transmission when the channel status is poor, the channel access of the system is efficient and saves energy.
Collapse
|
5
|
A Survey on Learning-Based Model Predictive Control: Toward Path Tracking Control of Mobile Platforms. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12041995] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
The learning-based model predictive control (LB-MPC) is an effective and critical method to solve the path tracking problem in mobile platforms under uncertain disturbances. It is well known that the machine learning (ML) methods use the historical and real-time measurement data to build data-driven prediction models. The model predictive control (MPC) provides an integrated solution for control systems with interactive variables, complex dynamics, and various constraints. The LB-MPC combines the advantages of ML and MPC. In this work, the LB-MPC technique is summarized, and the application of path tracking control in mobile platforms is discussed by considering three aspects, namely, learning and optimizing the prediction model, the controller design, and the controller output under uncertain disturbances. Furthermore, some research challenges faced by LB-MPC for path tracking control in mobile platforms are discussed.
Collapse
|
6
|
Zhou S, Pereida K, Zhao W, Schoellig AP. Bridging the Model-Reality Gap With Lipschitz Network Adaptation. IEEE Robot Autom Lett 2022. [DOI: 10.1109/lra.2021.3131698] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
7
|
Johnson CC, Quackenbush T, Sorensen T, Wingate D, Killpack MD. Using First Principles for Deep Learning and Model-Based Control of Soft Robots. Front Robot AI 2021; 8:654398. [PMID: 34017861 PMCID: PMC8129000 DOI: 10.3389/frobt.2021.654398] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2021] [Accepted: 03/29/2021] [Indexed: 11/23/2022] Open
Abstract
Model-based optimal control of soft robots may enable compliant, underdamped platforms to operate in a repeatable fashion and effectively accomplish tasks that are otherwise impossible for soft robots. Unfortunately, developing accurate analytical dynamic models for soft robots is time-consuming, difficult, and error-prone. Deep learning presents an alternative modeling approach that only requires a time history of system inputs and system states, which can be easily measured or estimated. However, fully relying on empirical or learned models involves collecting large amounts of representative data from a soft robot in order to model the complex state space–a task which may not be feasible in many situations. Furthermore, the exclusive use of empirical models for model-based control can be dangerous if the model does not generalize well. To address these challenges, we propose a hybrid modeling approach that combines machine learning methods with an existing first-principles model in order to improve overall performance for a sampling-based non-linear model predictive controller. We validate this approach on a soft robot platform and demonstrate that performance improves by 52% on average when employing the combined model.
Collapse
Affiliation(s)
- Curtis C Johnson
- Robotics and Dynamics Lab, Department of Mechanical Engineering, Brigham Young University, Provo, UT, United States
| | - Tyler Quackenbush
- Robotics and Dynamics Lab, Department of Mechanical Engineering, Brigham Young University, Provo, UT, United States
| | - Taylor Sorensen
- Perception, Control, and Cognition Lab, Department of Computer Science, Brigham Young University, Provo, UT, United States
| | - David Wingate
- Perception, Control, and Cognition Lab, Department of Computer Science, Brigham Young University, Provo, UT, United States
| | - Marc D Killpack
- Robotics and Dynamics Lab, Department of Mechanical Engineering, Brigham Young University, Provo, UT, United States
| |
Collapse
|
8
|
Nakka YK, Liu A, Shi G, Anandkumar A, Yue Y, Chung SJ. Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems. IEEE Robot Autom Lett 2021. [DOI: 10.1109/lra.2020.3044033] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
9
|
Elsisi M. Optimal design of nonlinear model predictive controller based on new modified multitracker optimization algorithm. INT J INTELL SYST 2020. [DOI: 10.1002/int.22275] [Citation(s) in RCA: 34] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Affiliation(s)
- Mahmoud Elsisi
- Industry 4.0 Implementation Center, Center for Cyber‐Physical System Innovation National Taiwan University of Science and Technology Taipei Taiwan
- Department of Electrical Engineering, Faculty of Engineering (Shoubra) Benha University Cairo Egypt
| |
Collapse
|
10
|
Grigorescu S, Trasnea B, Cocias T, Macesanu G. A survey of deep learning techniques for autonomous driving. J FIELD ROBOT 2020. [DOI: 10.1002/rob.21918] [Citation(s) in RCA: 349] [Impact Index Per Article: 87.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Affiliation(s)
- Sorin Grigorescu
- Artificial Intelligence, Elektrobit AutomotiveRobotics, Vision and Control Laboratory, Transilvania University of BrasovBrasov Romania
| | - Bogdan Trasnea
- Artificial Intelligence, Elektrobit AutomotiveRobotics, Vision and Control Laboratory, Transilvania University of BrasovBrasov Romania
| | - Tiberiu Cocias
- Artificial Intelligence, Elektrobit AutomotiveRobotics, Vision and Control Laboratory, Transilvania University of BrasovBrasov Romania
| | - Gigel Macesanu
- Artificial Intelligence, Elektrobit AutomotiveRobotics, Vision and Control Laboratory, Transilvania University of BrasovBrasov Romania
| |
Collapse
|
11
|
Kabzan J, Hewing L, Liniger A, Zeilinger MN. Learning-Based Model Predictive Control for Autonomous Racing. IEEE Robot Autom Lett 2019. [DOI: 10.1109/lra.2019.2926677] [Citation(s) in RCA: 98] [Impact Index Per Article: 19.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
12
|
Abstract
Recently, model predictive control (MPC) is increasingly applied to path tracking of mobile devices, such as mobile robots. The characteristics of these MPC-based controllers are not identical due to the different approaches taken during design. According to the differences in the prediction models, we believe that the existing MPC-based path tracking controllers can be divided into four categories. We named them linear model predictive control (LMPC), linear error model predictive control (LEMPC), nonlinear model predictive control (NMPC), and nonlinear error model predictive control (NEMPC). Subsequently, we built these four controllers for the same mobile robot and compared them. By comparison, we got some conclusions. The real-time performance of LMPC and LEMPC is good, but they are less robust to reference paths and positioning errors. NMPC performs well when the reference velocity is high and the radius of the reference path is small. It is also robust to positioning errors. However, the real-time performance of NMPC is slightly worse. NEMPC has many disadvantages. Like LMPC and LEMPC, it performs poorly when the reference velocity is high and the radius of the reference path is small. Its real-time performance is also not good enough.
Collapse
|
13
|
Rao Y, Yang F. Research on Path Tracking Algorithm of Autopilot Vehicle Based on Image Processing. INT J PATTERN RECOGN 2019. [DOI: 10.1142/s0218001420540130] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Smart cars are the result of the combination of the latest technological achievements in the fields of artificial intelligence, sensors, control science, computer, and network technology with the modern automobile industry. Intelligent cars usually have functions, such as automatic shifting, automatic driving, and automatic road condition recognition. The research of intelligent car technology involves many disciplines. This thesis focuses on the field of smart car visual navigation, focusing on image denoising, image information recognition, extraction, and pattern recognition control algorithms. The traditional trajectory tracking algorithm is mainly used in industrial computer or high-performance computer. The computational complexity leads to poor real-time control, and it is easily interfered by external complex terrain environment and internal disordered electromagnetic environment during vehicle driving. In general, on a regular basis, by the image analysis of the driver or the driver information, the image information is proposed using way trace processing technology, vehicle tracking control method and automatic driving rules. The simulation and experimental results show that the proposed control methods and rules used to carry out automatic driving vehicle are feasible. The algorithm reduces the complexity of the algorithm, improves the real-time and stability of the control and finally achieves a good trajectory tracking effect of the car on high-speed automatic driving.
Collapse
Affiliation(s)
- Yutai Rao
- Dean’s Office, Hubei Radio & TV University, Wuhan, Hubei, P. R. China
| | - Fan Yang
- Software Engineering Institute, Hubei Radio & TV University, Wuhan, Hubei, P. R. China
| |
Collapse
|
14
|
A constrained instantaneous learning approach for aerial package delivery robots: onboard implementation and experimental results. Auton Robots 2019. [DOI: 10.1007/s10514-019-09875-y] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
15
|
Path Tracking of Mining Vehicles Based on Nonlinear Model Predictive Control. APPLIED SCIENCES-BASEL 2019. [DOI: 10.3390/app9071372] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Path tracking of mining vehicles plays a significant role in reducing the working time of operators in the underground environment. Because the existing path tracking control of mining vehicles, based on model predictive control, is not very effective when the longitudinal velocity of the vehicle is above 2 m/s, we have devised a new controller based on nonlinear model predictive control. Then, we compare this new controller with the existing model predictive controller. In the results of our simulation, the tracking accuracy of our controller at the longitudinal velocity of 4 m/s is close to that of the existing model predictive controller, at the longitudinal velocity of 2 m/s. When longitudinal velocity is 4 m/s, the existing model predictive controller cannot drive the mining vehicle to track the given path, but our nonlinear model predictive controller can, and the maximum displacement error and heading error are 0.1382 m and 0.0589 rad, respectively. According to these results, we believe that this nonlinear model predictive controller can be used to improve the performance of the path tracking of mining vehicles.
Collapse
|
16
|
Dekker LG, Marshall JA, Larsson J. Experiments in feedback linearized iterative learning-based path following for center-articulated industrial vehicles. J FIELD ROBOT 2019. [DOI: 10.1002/rob.21864] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
17
|
MacTavish K, Paton M, Barfoot TD. Selective memory: Recalling relevant experience for long-term visual localization. J FIELD ROBOT 2018. [DOI: 10.1002/rob.21838] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Affiliation(s)
- Kirk MacTavish
- Institute for Aerospace Studies, Faculty of Applied Science & Engineering, University of Toronto; Toronto Ontario Canada
| | - Michael Paton
- Institute for Aerospace Studies, Faculty of Applied Science & Engineering, University of Toronto; Toronto Ontario Canada
| | - Timothy D. Barfoot
- Institute for Aerospace Studies, Faculty of Applied Science & Engineering, University of Toronto; Toronto Ontario Canada
| |
Collapse
|
18
|
Sherwin T, Easte M, Chen ATY, Wang KIK, Dai W. A Single RF Emitter-Based Indoor Navigation Method for Autonomous Service Robots. SENSORS 2018; 18:s18020585. [PMID: 29443906 PMCID: PMC5854970 DOI: 10.3390/s18020585] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/30/2017] [Revised: 01/26/2018] [Accepted: 02/08/2018] [Indexed: 11/17/2022]
Abstract
Location-aware services are one of the key elements of modern intelligent applications. Numerous real-world applications such as factory automation, indoor delivery, and even search and rescue scenarios require autonomous robots to have the ability to navigate in an unknown environment and reach mobile targets with minimal or no prior infrastructure deployment. This research investigates and proposes a novel approach of dynamic target localisation using a single RF emitter, which will be used as the basis of allowing autonomous robots to navigate towards and reach a target. Through the use of multiple directional antennae, Received Signal Strength (RSS) is compared to determine the most probable direction of the targeted emitter, which is combined with the distance estimates to improve the localisation performance. The accuracy of the position estimate is further improved using a particle filter to mitigate the fluctuating nature of real-time RSS data. Based on the direction information, a motion control algorithm is proposed, using Simultaneous Localisation and Mapping (SLAM) and A* path planning to enable navigation through unknown complex environments. A number of navigation scenarios were developed in the context of factory automation applications to demonstrate and evaluate the functionality and performance of the proposed system.
Collapse
Affiliation(s)
- Tyrone Sherwin
- Department of Electrical and Computer Engineering, The University of Auckland, Auckland 1023, New Zealand.
| | - Mikala Easte
- Department of Electrical and Computer Engineering, The University of Auckland, Auckland 1023, New Zealand.
| | - Andrew Tzer-Yeu Chen
- Department of Electrical and Computer Engineering, The University of Auckland, Auckland 1023, New Zealand.
| | - Kevin I-Kai Wang
- Department of Electrical and Computer Engineering, The University of Auckland, Auckland 1023, New Zealand.
| | - Wenbin Dai
- Department of Automation, Shanghai Jiao Tong University, Shanghai 200000, China.
| |
Collapse
|
19
|
Maiworm M, Limon D, Maria Manzano J, Findeisen R. Stability of Gaussian Process Learning Based Output Feedback Model Predictive Control. ACTA ACUST UNITED AC 2018. [DOI: 10.1016/j.ifacol.2018.11.047] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
20
|
|
21
|
Ostafew CJ, Schoellig AP, Barfoot TD. Robust Constrained Learning-based NMPC enabling reliable mobile robot path tracking. Int J Rob Res 2016. [DOI: 10.1177/0278364916645661] [Citation(s) in RCA: 101] [Impact Index Per Article: 12.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
This paper presents a Robust Constrained Learning-based Nonlinear Model Predictive Control (RC-LB-NMPC) algorithm for path-tracking in off-road terrain. For mobile robots, constraints may represent solid obstacles or localization limits. As a result, constraint satisfaction is required for safety. Constraint satisfaction is typically guaranteed through the use of accurate, a priori models or robust control. However, accurate models are generally not available for off-road operation. Furthermore, robust controllers are often conservative, since model uncertainty is not updated online. In this work our goal is to use learning to generate low-uncertainty, non-parametric models in situ. Based on these models, the predictive controller computes both linear and angular velocities in real-time, such that the robot drives at or near its capabilities while respecting path and localization constraints. Localization for the controller is provided by an on-board, vision-based mapping and navigation system enabling operation in large-scale, off-road environments. The paper presents experimental results, including over 5 km of travel by a 900 kg skid-steered robot at speeds of up to 2.0 m/s. The result is a robust, learning controller that provides safe, conservative control during initial trials when model uncertainty is high and converges to high-performance, optimal control during later trials when model uncertainty is reduced with experience.
Collapse
|
22
|
Clement L, Kelly J, Barfoot TD. Robust Monocular Visual Teach and Repeat Aided by Local Ground Planarity and Color-constant Imagery. J FIELD ROBOT 2016. [DOI: 10.1002/rob.21655] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Affiliation(s)
- Lee Clement
- Institute for Aerospace Studies; University of Toronto; Toronto ON Canada M3H 5T6
| | - Jonathan Kelly
- Institute for Aerospace Studies; University of Toronto; Toronto ON Canada M3H 5T6
| | - Timothy D. Barfoot
- Institute for Aerospace Studies; University of Toronto; Toronto ON Canada M3H 5T6
| |
Collapse
|