An official website of the United States government
This paper introduces a learning-based optimal control strategy enhanced with nonmodel-based state estimation to manage the complexities of lane-changing maneuvers in autonomous vehicles. Traditional approaches often depend on comprehensive system state information, which may not always be accessible or accurate due to dynamic traffic environments and sensor limitations. Our methodology dynamically adapts to these uncertainties and sensor noise by iteratively refining its control policy based on real-time sensor data and reconstructed states. We implemented an experimental setup featuring a scaled vehicle equipped with GPS, IMUs, and cameras, all processed through an Nvidia Jetson AGX Xavier board. This approach is pivotal as it addresses the limitations of simulations, which often fail to capture the complexity of dynamic real-world conditions. The results from real-world experiments demonstrate that our learning-based control system achieves smoother and more consistent lane-changing behavior compared to traditional direct measurement approaches. This paper underscores the effectiveness of integrating Adaptive Dynamic Programming (ADP) with state estimation techniques, as demonstrated through small-scale experiments. These experiments are crucial as they provide a practical validation platform that simulates real-world complexities, representing a significant advancement in the control systems used for autonomous driving.
more »
« less
High-Fidelity Teleoperated Scaled Vehicles for Research and Development of Intelligent Transportation Technologies
This paper presents a systematic design of high-fidelity tele-operated scaled vehicles to be used as a research and development platform for intelligent transportation technologies. Compared to computer simulation and full-scale physical tests, the use of high-fidelity scaled setups provides advantages on testing time and financial effectiveness. The physical design of the vehicles features a 1:14 scale with realistic appearance licensed by car manufacturers. Customized steering system and propulsion control provide high-fidelity maneuver characteristics. Remote control is deployed using a target-host structure over WiFi and can provide seamless switching between human driving and autonomous/assisted driving on the host side. Several possible solutions for real-time panoramic vision feedback are explored, with a tri-camera design based on parallel acquisition interfaces adopted. An adaptive color compression technique is developed to shorten the video streaming latency. A customized miniature LIDAR system is introduced to provide an ultra-small package for on-board installation. As a solution balancing between test fidelity and costs, the proposed scaled vehicles are especially suitable for validation tests during the early stage of research and development. With a long-term goal of developing a multi-vehicle traffic network test platform, ongoing and future work on the construction of scaled buildings and road systems is also discussed.
more »
« less
- Award ID(s):
- 1844238
- PAR ID:
- 10226006
- Date Published:
- Journal Name:
- ASME 2020 Dynamic Systems and Control Conference
- Volume:
- 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Integrated modeling of vehicle, tire and terrain is a fundamental challenge to be addressed for off-road autonomous navigation. The complexities arise due to lack of tools and techniques to predict the continuously varying terrain and environmental conditions and the resultant non-linearities. The solution to this challenge can now be found in the plethora of data driven modeling and control techniques that have gained traction in the last decade. Data driven modeling and control techniques rely on the system’s repeated interaction with the environment to generate a lot of data and then use a function approximator to fit a model for the physical system with the data. Getting good quality and quantity of data may involve extensive experimentation with the physical system impacting developer’s resource. The process is computationally expensive, and the overhead time required is high.High-fidelity simulators coupled with cloud-based containers can help ease the challenge of data ‘quality’ and ‘quantity’. Project Chrono is a multi-physics simulation engine that provides high-fidelity simulation capabilities with emphasis on flow and terrain modeling. With a host of libraries and APIs for industry accepted tools like MATLAB, Simulink and TensorFlow, Project Chrono proves to be a powerful research bed for data-driven modeling and control development for off-road navigation. Containers are lightweight virtual machines that take away repetitive configurations by setting up a computational environment, including all necessary dependencies and libraries. Docker encapsulates an end-to-end platform solution for heavy computation challenges of deep learning applications and allows fast development and testing. The synergy between the high-fidelity simulator and the compute outsourcing capabilities of cloud-based containers proves to be extremely beneficial for continuous integration and continuous deployment (CI/CD) for data driven modeling and control tasks. In the following work, we containerize a high-fidelity simulator (Project Chrono) to develop and validate data driven modeling and control algorithms for off-road autonomous navigation.more » « less
-
We are experiencing a revolution in vehicle operation, with fully automated robotaxis deployed and available for public use in major U.S. markets in 2023. These vehicles, while imperfect, already are arguably safer than the average human driver. Despite this rapid progress, there remain significant research and development problems that must be addressed; beyond this, there is an underdeveloped workforce for skilled researchers, developers, and practitioners in these areas, a fact that may delay necessary advances. We have created and run for two years a National Science Foundation funded Research Experience for Undergraduates (NSF REU) focused on solving both unmet research needs, and workforce development and pipeline programs. In our REU, which makes use of simulation and two full-scale, street-legal drive-by-wire electric vehicles with perception, planning, and control capabilities, our primary goals include to (1) provide hands-on experiences to undergraduate students who otherwise might not have research opportunities to learn fundamental theories in autonomous vehicle development, (2) allow students to design algorithms to practice software development and evaluation using real vehicles on real test courses, (3) strengthen their confidence, self-guided capabilities, and research skills, and (4) increase the number of students, including those from diverse backgrounds and technical disciplines, interested in graduate programs to ultimately provide a quality research and development workforce to both academia and industry. Over the initial two years, a cohort of 8 diverse students each year learned fundamental self-driving and computer networking skills including coding for drive-by-wire vehicles, computer vision, use of localization, and interpretation of richer sensor data, as well as network and communication protocols. The students were introduced to research ideation and publishing concepts, mentored in designing and testing hypotheses, and then involved in two challenges related to self-driving and networked vehicles. Two teams of 4 designed, implemented, tested various self-drive and V2X algorithms using real vehicles on a test course, analyzed/evaluated test results, wrote technical reports, and delivered presentations. After the summer program was over, the technical reports were published in peer reviewed conferences and journals. Survey results show that students attained significant & real-world computer science skills in autonomous vehicle development leveraging real vehicles available. The programs also increased research career interests and strengthened students’ confidence, self-guided capabilities, and research skills, while additionally supporting the development of workshop materials, simulators, and related content that provide valuable resources for others planning to develop an undergraduate curriculum to teach self-drive and networked vehicle development.more » « less
-
The development and applications of remotely operated and autonomous underwater vehicles have significantly increased in recent years. As these vehicles operate in the harsh underwater environment, demanding requirements for their design usually reflect in a high cost of underwater systems. However, with more readily available inexpensive electronics and powering systems, lower cost developments have been initiated. In the present work, several modifications of a low-cost remotely operated underwater platform are described. One is a construction of a two-degree-of-freedom arm for manipulating underwater objects. The second is an improvement of the propulsion control on the vehicle to allow for gradual variation of thrust forces instead of the original on/off mode. The third enhancement is a computer vision system for identifying underwater objects of interest that is applied for automated steering of the vehicle. Initial tests with these elements in a laboratory tank are presented and discussed. They include (1) autonomous detection of a target and maneuvering towards it, (2) grabbing and moving an object with manual remote control, and (3) the combined test with autonomous identification, grabbing, and moving of a target. The reported developments and test results can help other researchers pursuing low-cost developments of underwater vehicles.more » « less
-
To advance understanding of the multihazard performance of midrise cold-formed steel (CFS) construction, a unique multidisciplinary experimental program was conducted on the Large High-Performance Outdoor Shake Table (LHPOST) at the University of California, San Diego (UCSD). The centerpiece of this project involved earthquake and live fire testing of a full-scale 6-story CFS wall braced building. Initially, the building was subjected to seven earthquake tests of increasing motion intensity, sequentially targeting service, design, and maximum credible earthquake (MCE) demands. Subsequently, live fire tests were conducted on the earthquake-damaged building at two select floors. Finally, for the first time, the test building was subjected to two postfire earthquake tests, including a low-amplitude aftershock and an extreme near-fault target MCE-scaled motion. In addition, low-amplitude white noise and ambient vibration data were collected during construction and seismic testing phases to support identification of the dynamic state of the building system. This paper offers an overview of this unique multihazard test program and presents the system-level structural responses and physical damage features of the test building throughout the earthquake-fire-earthquake test phases, whereas the component-level seismic behavior of the shear walls and seismic design implications of CFS-framed building systems are discussed in a companion paper.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1115/DSCC2020-3173
