SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction

@article{Hu2021SHARPSR,
  title={SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction},
  author={Haimin Hu and Kensuke Nakamura and Jaime Fern{\'a}ndez Fisac},
  journal={IEEE Robotics and Automation Letters},
  year={2021},
  volume={7},
  pages={5591-5598}
}
Jointly achieving safety and efficiency in human-robot interaction settings is a challenging problem, as the robot’s planning objectives may be at odds with the human’s own intent and expectations. Recent approaches ensure safe robot operation in uncertain environments through a supervisory control scheme, sometimes called “shielding,” which overrides the robot’s nominal plan with a safety fallback strategy when a safety-critical event is imminent. These reactive “last-resort” strategies… 

Figures from this paper

Online Update of Safety Assurances Using Confidence-Based Predictions

This work proposes a Hamilton-Jacobi (HJ) reachability-based approach to overcome the challenge of compute the future human states online as the confidence parameter changes, and demonstrates the approach in several safety-critical autonomous driving scenarios, involving a state-of-the- art deep learning-based prediction model.

Active Uncertainty Reduction for Human-Robot Interaction: An Implicit Dual Control Approach

This paper presents a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm that relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods.

Active Uncertainty Learning for Human-Robot Interaction: An Implicit Dual Control Approach

This paper presents a novel algorithmic approach to enable active uncertainty learning for human-in-the-loop motion planning based on the implicit dual control paradigm that relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods.

Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles

A probabilistic run-time monitor that detects when a “harmful” prediction failure occurs, i.e., a task-relevant failure detector is developed by propagating trajectory prediction errors to the planning cost to reason about their impact on the AV.

Leveraging Non-Experts and Formal Methods to Automatically Correct Robot Failures

  • Sanne van Waveren
  • Computer Science
    2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
  • 2022
This research aims to integrate elements of formal synthesis approaches into computational human-robot interaction to develop verifiable robots that can automatically correct their policy using non-expert feedback on the fly.

MPOGames: Efficient Multimodal Partially Observable Dynamic Games

This work proposes MPOGames, a method for efficiently solving MaxEnt dynamic games that captures the interactions between local Nash equilibria and shows the importance of uncertainty-aware game theoretic methods via a two-agent merge case study.

References

SHOWING 1-10 OF 31 REFERENCES

Probabilistically Safe Robot Planning with Confidence-Based Human Predictions

This paper observes that how "rational" human actions appear under a particular model can be viewed as an indicator of that model's ability to describe the human's current motion, and combines worst-case tracking error guarantees for the physical robot with probabilistic time-varying human predictions, yielding a quantitative, Probabilistic safety certificate.

Planning for cars that coordinate with people: leveraging effects on human actions for planning and active information gathering over human internal state

This work introduces a formulation of interaction with human-driven vehicles as an underactuated dynamical system, in which the robot’s actions have consequences on the state of the autonomous car, but also on the human actions and thus thestate of the human- driven car.

Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perception

A novel analytical approach is introduced that poses safe trajectory planning under occlusions as a hybrid zero-sum dynamic game between the autonomous vehicle (evader) and an initially hidden traffic participant (pursuer).

Contingency Planning Over Probabilistic Obstacle Predictions for Autonomous Road Vehicles

Simulation results show that the contingency planner allows for a more aggressive driving style than planning a single path without compromising the overall safety of the robot.

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics

  • Shuo LiO. Bastani
  • Computer Science
    2020 IEEE International Conference on Robotics and Automation (ICRA)
  • 2020
This work proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems, and proposes to use a tube-based robust nonlinear model predictive controller (NMPC) as the backup controller.

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.

Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning

This work generalizes the reinforcement learning formulation to handle all optimal control problems in the reach-avoid category, and demonstrates the use of this formulation with deep reinforcement learning methods, retaining zero-violation guarantees by treating the approximate solutions as untrusted oracles in a model-predictive supervisory control framework.

Hierarchical Game-Theoretic Planning for Autonomous Vehicles

This paper introduces a novel game-theoretic trajectory planning algorithm for autonomous driving that enables real-time performance by hierarchically decomposing the underlying dynamic game into a long-horizon “strategic” game with simplified dynamics and full information structure, and a short-Horizon ‘tactical’ game with full dynamics and a simplified information structure.

The Heavy Tail Safety Ceiling

Autonomous vehicles will need to be robust in handling novelty, and will additionally need a way to detect that they are encountering a surprise so that they can remain safe in the face of uncertainty.

Learning Control Barrier Functions from Expert Demonstrations

These are the first results that learn provably safe control barrier functions from data, agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded.