• Corpus ID: 245131331

Cooperation for Scalable Supervision of Autonomy in Mixed Traffic

  title={Cooperation for Scalable Supervision of Autonomy in Mixed Traffic},
  author={Cameron Hickert and Sirui Li and Cathy Wu},
Improvements in autonomy offer the potential for positive outcomes in a number of domains, yet guaranteeing their safe deployment is difficult. This work investigates how humans can intelligently supervise agents to achieve some level of safety even when performance guarantees are elusive. The motivating research question is: In safety-critical settings, can we avoid the need to have one human supervise one machine at all times? The paper formalizes this ‘scaling supervision’ problem, and… 

Figures and Tables from this paper


Flow: A Modular Learning Framework for Mixed Autonomy Traffic
The suitability of deep reinforcement learning (RL) for overcoming challenges in a low AV-adoption regime is studied and a modular learning framework is presented, which leverages deep RL to address complex traffic dynamics.
Learning and Optimization for Mixed Autonomy Systems - A Mobility Context
It is demonstrated that deep reinforcement learning (RL) can serve as a unifying framework for studying the behavior of disparate and complex scenarios common in mixed autonomy systems, and that deep RL has the potential to scale to high-dimensional control systems, such as traffic networks and other mixed autonomous systems.
Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving
This paper outlines a case study of an intersection scenario involving multiple traffic participants and proposes a generic approach to enforce probabilistic guarantees on an RL agent that outperforms a rule-based heuristic approach in terms of efficiency while exhibiting strong guarantees on safety.
A Lyapunov-based Approach to Safe Reinforcement Learning
This work defines and presents a method for constructing Lyapunov functions, which provide an effective way to guarantee the global safety of a behavior policy during training via a set of local, linear constraints.
Multi-Adversarial Safety Analysis for Autonomous Vehicles
This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems and proposes a modeling strategy in the formulation that accounts for subtle interactions between agents, and compares its Hamiltonian results to other baselines.
On infusing reachability-based safety assurance within planning frameworks for human–robot vehicle interactions
A minimally interventional safety controller operating within an autonomous vehicle control stack with the role of ensuring collision-free interaction with an externally controlled counterpart while respecting static obstacles such as a road boundary wall is introduced.
Safe Model-based Reinforcement Learning with Stability Guarantees
This paper presents a learning algorithm that explicitly considers safety, defined in terms of stability guarantees, and extends control-theoretic results on Lyapunov stability verification and shows how to use statistical models of the dynamics to obtain high-performance control policies with provable stability certificates.
Multi-Agent Systems for Search and Rescue Applications
Multi-agent systems are not currently ready for deployment in search and rescue applications; however, progress is being made in a number of critical domains.
Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach
This paper derives conditions under which the operator allocation problem is indexable, enabling the use of the Whittle index heuristic, and applies these conditions to two types of transitions commonly seen in remote robot supervision systems.
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
This work formalizes human intervention for RL and shows how to reduce the human labor required by training a supervised learner to imitate the human's intervention decisions, and outlines extensions of the scheme that are necessary if the authors are to train model-free agents without a single catastrophe.