Corpus ID: 226227199

Adversarial Attacks on Optimization based Planners

@article{Vemprala2020AdversarialAO,
  title={Adversarial Attacks on Optimization based Planners},
  author={Sai Vemprala and A. Kapoor},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.00095}
}
  • Sai Vemprala, A. Kapoor
  • Published 2020
  • Computer Science
  • ArXiv
  • Trajectory planning is a key piece in the algorithmic architecture of a robot. Trajectory planners typically use iterative optimization schemes for generating smooth trajectories that avoid collisions and are optimal for tracking given the robot's physical specifications. Starting from an initial estimate, the planners iteratively refine the solution so as to satisfy the desired constraints. In this paper, we show that such iterative optimization based planners can be vulnerable to adversarial… CONTINUE READING
    1 Citations

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 30 REFERENCES
    Funnel libraries for real-time robust feedback motion planning
    • 159
    • PDF
    Fast Safe Mission Plans for Autonomous Vehicles
    • 6
    • PDF
    FASTER: Fast and Safe Trajectory Planner for Flights in Unknown Environments
    • 30
    • PDF
    Safe Local Exploration for Replanning in Cluttered Unknown Environments for Microaerial Vehicles
    • 38
    • PDF
    CHOMP: Gradient optimization techniques for efficient motion planning
    • 578
    • Highly Influential
    • PDF
    An Efficient Reachability-Based Framework for Provably Safe Autonomous Navigation in Unknown Environments
    • 20
    • PDF
    Provably safe robot navigation with obstacle uncertainty
    • 28
    • PDF
    Polynomial Trajectory Planning for Aggressive Quadrotor Flight in Dense Indoor Environments
    • 331
    • PDF
    FaSTrack: A modular framework for fast and guaranteed safe motion planning
    • 114
    • PDF
    STOMP: Stochastic trajectory optimization for motion planning
    • 498
    • PDF