Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 152 for “"Safety constraints"”.

  1. Safety Constraints in Control Systems

    … the University of Washington on topics such as: safety constraints, controlled invariant sets, Markov chains, Markov decision processes, and swarm guidance. As autonomous systems become more prevalent, great care must be taken to ensure that they remain in well-understood operating regimes, …

    washington Repository record for Safety Constraints in Control Systems (opens in a new tab)

  2. Contextual Bandits with hard-safety constraints

    … Contextual Bandit algorithms with stage-wise constraints have attracted much attention due to their applicability in real-world contexts such as determining optimal dosages or ad policies. Nonetheless, a drawback is that they ensure high-probability guarantees only for the expected cost …

    bu Repository record for Contextual Bandits with hard-safety constraints (opens in a new tab)

  3. Learning and Control with Delay and Safety Constraints in Networked Systems

    Many physical systems have underlying safety or capacity considerations that require that the control policy employed ensures the satisfaction of a set of constraints. For instance, in a data network, in addition to maximizing the utility of the users, the controller has to maintain necessary link …

    tamu Repository record for Learning and Control with Delay and Safety Constraints in Networked Systems (opens in a new tab)

  4. JOINT LEARNING OF UNKNOWN SAFETY CONSTRAINTS AND CONTROL POLICIES IN REINFORCEMENT LEARNING

    … presents the crucial challenge of ensuring safety. Traditional safe RL approaches have predominantly focused on incorporating predefined safety constraints into the policy learning process. However, this reliance on predefined safety constraints poses limitations in dynamic and unpredictable …

    wvu Repository record for JOINT LEARNING OF UNKNOWN SAFETY CONSTRAINTS AND CONTROL POLICIES IN REINFORCEMENT LEARNING (opens in a new tab)

  5. Density Control of Multi-Agent Systems with Safety Constraints: A Markov Chain Approach

    … commanding of the agents by imposing mission constraints on the distribution. We also make some connections with decentralized low-level motion control. This dissertation proposes a Markov chain based method to control the density distribution of the whole system where the implementation can …

    washington Repository record for Density Control of Multi-Agent Systems with Safety Constraints: A Markov Chain Approach (opens in a new tab)

  6. Convex Approach to Data-Driven Optimal Control With Safety Constraints Using Linear Transfer Operator

    … solution to the optimal control problem with safety constraints for a class of control-affine nonlinear systems. Designing optimal control satisfying safety constraints is a problem of interest in various applications, including robotics, power systems, transportation networks, and …

    clemson Repository record for Convex Approach to Data-Driven Optimal Control With Safety Constraints Using Linear Transfer Operator (opens in a new tab)

  7. Reinforcement Learning Benchmarking for Sustainable Energy Systems: Perturbation Robustness, Safety Constraints, and Multi-Agent Coordination

    … experimental axes: perturbation robustness, safety constraints, and multi-agent coordination. Our evaluation spans 116 unique configurations totaling over 310 training runs. Several findings challenge conventional expectations. Perturbation sensitivity varies by over an order of magnitude …

    vt Repository record for Reinforcement Learning Benchmarking for Sustainable Energy Systems: Perturbation Robustness, Safety Constraints, and Multi-Agent Coordination (opens in a new tab)

  8. Towards safe and efficient offline reinforcement learning: learning safety constraints and expressive policies via generative modeling

    … from static datasets in a way that both respects safety constraints and captures complex action distributions. This thesis investigates algorithmic advancements in offline reinforcement learning (RL) with a focus on (a) ensuring policy safety under uncertainty and (b) enhancing the expressiveness …

    iastate Repository record for Towards safe and efficient offline reinforcement learning: learning safety constraints and expressive policies via generative modeling (opens in a new tab)

  9. Software Architecture for Reducing Testing Effort while Ensuring Safety in Autonomous Road Vehicles

    … proposes a software architecture which separates safety constraints from functionality within the context of decision making in autonomous road vehicles. The intention of the separation is to avoid having to recertify safety requirements when updating functionality. The scope is limited to only …

    chalmers Repository record for Software Architecture for Reducing Testing Effort while Ensuring Safety in Autonomous Road Vehicles (opens in a new tab)

  10. Fast numerical algorithms for optimal robot motion planning

    … as buildings or other cars, as well as provide safety for pedestrians. Our approach to solve the optimal planning problem is to use the optimal control formalism borrowed from the control theory. In this setting, safety constraints for either a robot or its surroundings are defined as obstacles, …

    uiuc Repository record for Fast numerical algorithms for optimal robot motion planning (opens in a new tab)

  11. Analysis of Various Adaptive Cruise Controllers via Experimental Implementation

    … being studied for driver convenience and safety automation systems for production vehicles: electronic stability control, adaptive cruise control, lane keeping, and obstacle avoidance. Presented here are some novel control framework that gives formal guarantees of correctness that go …

    tamu Repository record for Analysis of Various Adaptive Cruise Controllers via Experimental Implementation (opens in a new tab)

  12. Multi-Robot Cooperative System for Complex Aerospace Manipulation Tasks: Theory and Application

    … disturbances are only partially known, and when safety constraints must be enforced during physical interaction. This dissertation develops a two-layer control framework for resilient multi-robot manipulation under uncertainty, with emphasis on space servicing, satellite stabilization, aerial …

    unm Repository record for Multi-Robot Cooperative System for Complex Aerospace Manipulation Tasks: Theory and Application (opens in a new tab)

  13. On Safety in Sequential Decision Learning

    … methods and algorithms to overcome critical safety challenges in sequential decision-learning systems across various applications, from recommendation systems to large language models and robotics. The research explores three key aspects of safety: per-time-step constraint satisfaction, …

    tamu Repository record for On Safety in Sequential Decision Learning (opens in a new tab)

  14. Augmenting a Hazard Analysis Method with Error Propagation Information for Safety-Critical Systems

    Safety-critical systems need specific activities in the software development life cycle to ensure that the system will operate safely. The objective of this dissertation is to develop a new safety analysis method to identify hazards. The method uses error propagation information and the internal …

    clemson Repository record for Augmenting a Hazard Analysis Method with Error Propagation Information for Safety-Critical Systems (opens in a new tab)

  15. Safety-critical control and optimization of traffic systems

    … improve efficiency while guaranteeing safety. This dissertation develops control and optimization methods for traffic systems with an emphasis on safety-critical operation, vehicle coordination, and recovery from unsafe conditions. The first part addresses adaptive traffic light control …

    bu Repository record for Safety-critical control and optimization of traffic systems (opens in a new tab)

  16. Safe Exploration of Reinforcement Learning Agents in Uncertain and Black-Box Environments

    … However, training and deploying RL agents in safety-critical, real-world environments remains a major challenge. Many real-world applications lack a simulator or offline dataset that captures dynamics, sensing artefacts, and long-tail edge cases well enough, so effective policies often require …

    whiterose Download PDF for Safe Exploration of Reinforcement Learning Agents in Uncertain and Black-Box Environments (opens in a new tab)

  17. Safety-critical optimal control in autonomous traffic systems

    … to solve this problem. This work focuses on the safety-critical optimal control of CAVs in autonomous traffic systems. The dissertation starts with the roundabout problem of controlling CAVs travelling through a roundabout so as to jointly minimize their travel time, energy consumption, and …

    bu Repository record for Safety-critical optimal control in autonomous traffic systems (opens in a new tab)

  18. Electric Bus Charging Scheduling based on Deep Reinforcement Learning

    … is to devise intelligent, scalable, and safety-aware charging scheduling algorithms tailored for practical, uncertain environments. Initially, we identify critical limitations in conventional optimization techniques, such as Mixed Integer Linear Programming (MILP) and Robust Optimization …

    guelph Repository record for Electric Bus Charging Scheduling based on Deep Reinforcement Learning (opens in a new tab)

  19. Safety-critical multi-agent control and coordination for autonomous vehicles: barrier functions, learning, and deployment

    … and merging roadways. This dissertation advances safety-critical multi-agent control and coordination for autonomous vehicles through a sequence of integrated contributions. First, motivated by the limitations of conventional time-driven control methods, event-triggered and self-triggered control …

    bu Repository record for Safety-critical multi-agent control and coordination for autonomous vehicles: barrier functions, learning, and deployment (opens in a new tab)

  20. Reference Governor For Air-Conditioner

    … controllers with the capability to enforce constraints to ensure safe and reliable operation. The RG makes minimal adjustments to the reference room temperature setpoint to ensure that the refrigerant entering the compressor is super-heated, thereby preventing potential damage. Designing the …

    unm Repository record for Reference Governor For Air-Conditioner (opens in a new tab)

Page 1 of 8