Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (7 results)

  • Thesis
  • Peer Reviewed
UC Berkeley Electronic Theses and Dissertations (2024)

The advancement of autonomous driving technology is revolutionizing mobility, offering safer, more efficient, and sustainable solutions across various domains. Beyond the progress achieved on public roads, tightly constrained environments—from parking lots to cargo warehouses, cluttered spaces filled with obstacles, and industrial construction sites—present unique challenges that demand innovative solutions. This thesis aims to extend the capabilities of autonomous vehicle systems to these complex environments, focusing on enhancing their safety, efficiency, and usability at both the vehicle level and fleet level.

For vehicle-level automation, one of the focuses is the development of methods for motion and intent prediction in less-structured areas, employing a multimodal approach that integrates convolutional neural networks (CNNs) and transformers. Such accurate predictions improve autonomous vehicles' situational awareness, enabling safer and more efficient navigation through tight spaces, whether in parking lots or similar environments.

Additionally, the thesis explores the integration of learning-based strategies with control algorithms to enhance vehicle operation in constrained settings. This includes the design of hierarchical collision avoidance and multi-vehicle conflict resolution strategies, leveraging machine learning algorithms to facilitate seamless coordination and operation of autonomous systems in spaces where traditional approaches may quickly become intractable.

The third contribution relates to optimizing the fleet-level efficiency of a fleet of autonomous systems in constrained environments. By employing traffic simulation coupled with autonomous control and strategic assignment policies, the last part of this thesis addresses complex fleet operational challenges such as kinematically feasible maneuvers, multi-vehicle interactions, and traffic flow to improve overall time and space efficiency.

    Cover page: Safe and Efficient Control of Autonomous Vehicles in Tightly Constrained Environments
    • Article
    • Peer Reviewed
    UC Berkeley Previously Published Works (2023)
    This work presents a distributed algorithm for resolving cooperative multi-vehicle conflicts in highly constrained spaces. By formulating the conflict resolution problem as a Multi-Agent Reinforcement Learning (RL) problem, we can train a policy offline to drive the vehicles towards their destinations safely and efficiently in a simplified discrete environment. During the online execution, each vehicle first simulates the interaction among vehicles with the trained policy to obtain its strategy, which is used to guide the computation of a reference trajectory. A distributed Model Predictive Controller (MPC) is then proposed to track the reference while avoiding collisions. The preliminary results show that the combination of RL and distributed MPC has the potential to guide vehicles to resolve conflicts safely and smoothly while being less computationally demanding than the centralized approach.
      • Article
      • Peer Reviewed
      UC Berkeley Previously Published Works (2020)
      The problem of autonomous parking of vehicle fleets is addressed in this paper. We present a system-level modeling and control framework which allows investigating different vehicle parking strategies while taking into account path planning and collision avoidance. The proposed approach decouples the problem into a centralized parking spot allocation and path generation, and a decentralized collision avoidance control. This paper presents the hierarchical framework and algorithmic details. Extensive simulations are used to assess several allocation strategies in terms of total fleet parking time and queue length. In particular, we observe that when parking large vehicle fleets, a phenomenon similar to Braess's paradox occurs.
        Creative Commons 'BY' version 4.0 license
        • Article
        • Peer Reviewed
        UC Berkeley Previously Published Works (2021)
        We present a hierarchical control approach for maneuvering an autonomous vehicle (AV) in tightly-constrained environments where other moving AVs and/or human driven vehicles are present. A two-level hierarchy is proposed: a high-level data-driven strategy predictor and a lower-level model-based feedback controller. The strategy predictor maps an encoding of a dynamic environment to a set of high-level strategies via a neural network. Depending on the selected strategy, a set of time-varying hyperplanes in the AV's position space is generated online and the corresponding halfspace constraints are included in a lower-level model-based receding horizon controller. These strategy-dependent constraints drive the vehicle towards areas where it is likely to remain feasible. Moreover, the predicted strategy also informs switching between a discrete set of policies, which allows for more conservative behavior when prediction confidence is low. We demonstrate the effectiveness of the proposed data-driven hierarchical control framework in a two-car collision avoidance scenario through simulations and experiments on a 1/10 scale autonomous car platform where the strategy-guided approach outperforms a model predictive control baseline in both cases.
          Creative Commons 'BY' version 4.0 license
          • Article
          • Peer Reviewed
          UC Berkeley Previously Published Works (2022)
            Creative Commons 'BY' version 4.0 license
            • Article
            • Peer Reviewed
            UC Berkeley Previously Published Works (2023)
            This work presents a novel hierarchical approach to increase Battery Electric Buses (BEBs) utilization in transit fleets. The proposed approach relies on three key components. A learning-based BEB digital twin cloud platform is used to accurately predict BEB charge consumption on a per vehicle, per driver, and per route basis, and accurately predict the time-to-charge BEB batteries to any level. These predictions are then used by a Predictive Block Assignment module to maximize the BEB fleet utilization. This module computes the optimal BEB daily assignment and charge management strategy. A Depot Parking and Charging Queue Management module is used to autonomously park and charge the vehicles based on their charging demands. The paper discusses the technical approach and benefits of each level in the architecture and concludes with a realistic simulations study. The study shows that if our approach is employed BEB fleet utilization can increase by a 50% compared to state-of-the-art methods.
              • Article
              • Peer Reviewed
              UC Berkeley Previously Published Works (2020)
              We investigate the problem of predicting driver behavior in parking lots, an environment which is less structured than typical road networks and features complex, interactive maneuvers in a compact space. Using the CARLA simulator, we develop a parking lot environment and collect a dataset of human parking maneuvers. We then study the impact of model complexity and feature information by comparing a multi-modal Long Short-Term Memory (LSTM) prediction model and a Convolution Neural Network LSTM (CNN-LSTM) to a physics-based Extended Kalman Filter (EKF) baseline. Our results show that 1) intent can be estimated well (roughly 85% top-1 accuracy and nearly 100% top-3 accuracy with the LSTM and CNN-LSTM model); 2) knowledge of the human driver's intended parking spot has a major impact on predicting parking trajectory; and 3) the semantic representation of the environment improves long term predictions.
                Creative Commons 'BY' version 4.0 license
                Top