A Scalable and Parallelizable Digital Twin Framework for Sustainable Sim2Real Transition of Multi-Agent Reinforcement Learning Systems

This work presents a sustainable multi-agent deep reinforcement learning framework capable of selectively scaling parallelized training workloads on-demand, and transferring the trained policies from simulation to reality using minimal hardware resources. We introduce AutoDRIVE Ecosystem as an enabling digital twin framework to train, deploy, and transfer cooperative as well as competitive multi-agent reinforcement learning policies from simulation to reality. Particularly, we first investigate an intersection traversal problem of 4 cooperative vehicles (Nigel) that share limited state information in single as well as multi-agent learning settings using a common policy approach. We then investigate an adversarial autonomous racing problem of 2 vehicles (F1TENTH) using an individual policy approach. In either set of experiments, a decentralized learning architecture was adopted, which allowed robust training and testing of the policies in stochastic environments. The agents were provided with realistically sparse observation spaces, and were restricted to sample control actions that implicitly satisfied the imposed kinodynamic and safety constraints. The experimental results for both problem statements are reported in terms of quantitative metrics and qualitative remarks for training as well as deployment phases. We also discuss agent and environment parallelization techniques adopted to efficiently accelerate MARL training, while analyzing their computational performance. Finally, we demonstrate a resource-aware transition of the trained policies from simulation to reality using the proposed digital twin framework.

Autonomy Oriented Digital Twins for Real2Sim2Real Autoware Deployment

Modeling and simulation of autonomous vehicles plays a crucial role in achieving enterprise-scale realization that aligns with technical, business and regulatory requirements. Contemporary trends in digital lifecycle treatment have proven beneficial to support SBD as well as V&V of these complex systems. Although, the development of appropriate fidelity simulation models capable of capturing the intricate real-world physics and graphics (real2sim), while enabling real-time interactivity for decision-making, has remained a challenge. Nevertheless, recent advances in AI-based tools and workflows, such as online deep-learning algorithms leveraging live-streaming data sources, offer the tantalizing potential for real-time system-identification and adaptive modeling to simulate vehicles, environments, as well as their interactions. This transition from virtual prototypes to digital twins not only improves simulation fidelity and real-time factor, but can also support the development of online adaption/augmentation techniques that can help bridge the gap between simulation and reality (sim2real). In such a milieu, this work focuses on developing autonomy-oriented digital twins of vehicles across different scales and configurations to help support the streamlined development and deployment of Autoware stack, using a unified real2sim2real toolchain. Particularly, the core deliverable for this project was to integrate the Autoware stack with AutoDRIVE Ecosystem to demonstrate end-to-end task of map-based autonomous navigation. This work discusses the development of vehicle and environment digital twins using AutoDRIVE Ecosystem, along with various APIs and HMIs to connect with the same, followed by a detailed section on AutoDRIVE-Autoware integration. Furthermore, this study describes the first-ever off-road deployment of the Autoware stack, expanding the ODD beyond on-road autonomous navigation.

Towards Validation of Autonomous Vehicles Across Scales using an Integrated Digital Twin Framework

Autonomous vehicle platforms of varying spatial scales are employed within the research and development spectrum based on space, safety and monetary constraints. However, deploying and validating autonomy algorithms across varying operational scales presents challenges due to scale-specific dynamics, sensor integration complexities, computational constraints, regulatory considerations, environmental variability, interaction with other traffic participants and scalability concerns. In such a milieu, this work focuses on developing a unified framework for modeling and simulating digital twins of autonomous vehicle platforms across different scales and operational design domains (ODDs) to help support the streamlined development and validation of autonomy software stacks. Particularly, this work discusses the development of digital twin representations of 4 autonomous ground vehicles, which span across 3 different scales and target 3 distinct ODDs. We study the adoption of these autonomy-oriented digital twins to deploy a common autonomy software stack with an aim of end-to-end map-based navigation to achieve the ODD-specific objective(s) for each vehicle. Finally, we also discuss the flexibility of the proposed framework to support virtual, hybrid as well as physical testing with seamless sim2real transfer.

Nigel -- Mechatronic Design and Robust Sim2Real Control of an Over-Actuated Autonomous Vehicle

Simulation to reality (sim2real) transfer from a dynamics and controls perspective usually involves re-tuning or adapting the designed algorithms to suit real-world operating conditions, which often violates the performance guarantees established originally. This work presents a generalizable framework for achieving reliable sim2real transfer of autonomy-oriented control systems using multi-model multi-objective robust optimal control synthesis, which lends well to uncertainty handling and disturbance rejection with theoretical guarantees. Particularly, this work is centered around an actuation-redundant scaled autonomous vehicle called Nigel, with independent all-wheel drive and independent all-wheel steering architecture, whose enhanced configuration space bodes well for robust control applications. To this end, we present a systematic study on the complete mechatronic design, dynamics modeling, parameter identification, and robust stabilizing as well as steady-state tracking control of Nigel using the proposed framework, with experimental validation.

Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem

This work presents a modular and parallelizable multi-agent deep reinforcement learning framework for imbibing cooperative as well as competitive behaviors within autonomous vehicles. We introduce AutoDRIVE Ecosystem as an enabler to develop physically accurate and graphically realistic digital twins of Nigel and F1TENTH, two scaled autonomous vehicle platforms with unique qualities and capabilities, and leverage this ecosystem to train and deploy multi-agent reinforcement learning policies. We first investigate an intersection traversal problem using a set of cooperative vehicles (Nigel) that share limited state information with each other in single as well as multi-agent learning settings using a common policy approach. We then investigate an adversarial head-to-head autonomous racing problem using a different set of vehicles (F1TENTH) in a multi-agent learning setting using an individual policy approach. In either set of experiments, a decentralized learning architecture was adopted, which allowed robust training and testing of the approaches in stochastic environments, since the agents were mutually independent and exhibited asynchronous motion behavior. The problems were further aggravated by providing the agents with sparse observation spaces and requiring them to sample control commands that implicitly satisfied the imposed kinodynamic as well as safety constraints. The experimental results for both problem statements are reported in terms of quantitative metrics and qualitative remarks for training as well as deployment phases.

Towards Sim2Real Transfer of Autonomy Algorithms using AutoDRIVE Ecosystem

The engineering community currently encounters significant challenges in the development of intelligent transportation algorithms that can be transferred from simulation to reality with minimal effort. This can be achieved by robustifying the algorithms using domain adaptation methods and/or by adopting cutting-edge tools that help support this objective seamlessly. This work presents AutoDRIVE, an openly accessible digital twin ecosystem designed to facilitate synergistic development, simulation and deployment of cyber-physical solutions pertaining to autonomous driving technology; and focuses on bridging the autonomy-oriented simulation-to-reality (sim2real) gap using the proposed ecosystem. In this paper, we extensively explore the modeling and simulation aspects of the ecosystem and substantiate its efficacy by demonstrating the successful transition of two candidate autonomy algorithms from simulation to reality to help support our claims: (i) autonomous parking using probabilistic robotics approach; (ii) behavioral cloning using deep imitation learning. The outcomes of these case studies further strengthen the credibility of AutoDRIVE as an invaluable tool for advancing the state-of-the-art in autonomous driving technology.

Towards Mechatronics Approach of System Design, Verification and Validation for Autonomous Vehicles

Modern-day autonomous vehicles are increasingly becoming complex multidisciplinary systems composed of mechanical, electrical, electronic, computing and information sub-systems. Furthermore, the individual constituent technologies employed for developing autonomous vehicles have started maturing up to a point, where it seems beneficial to start looking at the synergistic integration of these components into sub-systems, systems, and potentially, system-of-systems. Hence, this work applies the principles of mechatronics approach of system design, verification and validation for the development of autonomous vehicles. Particularly, we discuss leveraging multidisciplinary co-design practices along with virtual, hybrid and physical prototyping and testing within a concurrent engineering framework to develop and validate a scaled autonomous vehicle using the AutoDRIVE ecosystem. We also describe a case-study of autonomous parking application using a modular probabilistic framework to illustrate the benefits of the proposed approach.

AutoDRIVE: A Comprehensive, Flexible and Integrated Cyber-Physical Ecosystem for Enhancing Autonomous Driving Research and Education

Prototyping and validating hardware-software components, sub-systems and systems within the intelligent transportation system-of-systems framework requires a modular yet flexible and open-access ecosystem. This work presents our attempt towards developing such a comprehensive research and education ecosystem, called AutoDRIVE, for synergistically prototyping, simulating and deploying cyber-physical solutions pertaining to autonomous driving as well as smart city management. AutoDRIVE features both software as well as hardware-in-the-loop testing interfaces with openly accessible scaled vehicle and infrastructure components. The ecosystem is compatible with a variety of development frameworks, and supports both single and multi-agent paradigms through local as well as distributed computing. Most critically, AutoDRIVE is intended to be modularly expandable to explore emergent technologies, and this work highlights various complementary features and capabilities of the proposed ecosystem by demonstrating four such deployment use-cases: (i) autonomous parking using probabilistic robotics approach for mapping, localization, path planning and control; (ii) behavioral cloning using computer vision and deep imitation learning; (iii) intersection traversal using vehicle-to-vehicle communication and deep reinforcement learning; and (iv) smart city management using vehicle-to-infrastructure communication and internet-of-things.

AutoDRIVE -- Technical Report

This work presents AutoDRIVE, a comprehensive research and education platform for implementing and validating intelligent transportation algorithms pertaining to vehicular autonomy as well as smart city management. It is an openly accessible platform featuring a 1:14 scale car with realistic drive and steering actuators, redundant sensing modalities, high-performance computational resources, and standard vehicular lighting system. Additionally, the platform also offers a range of modules for rapid design and development of the infrastructure. The AutoDRIVE platform encompasses Devkit, Simulator and Testbed, a harmonious trio to develop, simulate and deploy autonomy algorithms. It is compatible with a variety of software development packages, and supports single as well as multi-agent paradigms through local and distributed computing. AutoDRIVE is a product-level implementation, with a vast scope for commercialization. This versatile platform has numerous applications, and they are bound to keep increasing as new features are added. This work demonstrates four such applications including autonomous parking, behavioural cloning, intersection traversal and smart city management, each exploiting distinct features of the platform.