Case Studies for Computing Density of Reachable States for Safe Autonomous Motion Planning
Not on the map. Why?
Abstract (arXiv)
Density of the reachable states can help understand the risk of safety-critical systems, especially in situations when worst-case reachability is too conservative. Recent work provides a data-driven approach to compute the density distribution of autonomous systems' forward reachable states online. In this paper, we study the use of such approach in combination with model predictive control for verifiable safe path planning under uncertainties. We first use the learned density distribution to compute the risk of collision online. If such risk exceeds the acceptable threshold, our method will plan for a new path around the previous trajectory, with the risk of collision below the threshold. Our method is well-suited to handle systems with uncertainties and complicated dynamics as our data-driven approach does not need an analytical form of the systems' dynamics and can estimate forward state density with an arbitrary initial distribution of uncertainties. We design two challenging scenarios (autonomous driving and hovercraft control) for safe motion planning in environments with obstacles under system uncertainties. We first show that our density estimation approach can reach a similar accuracy as the Monte-Carlo-based method while using only 0.01X training samples. By leveraging the estimated risk, our algorithm achieves the highest success rate in goal reaching when enforcing the safety rate above 0.99.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 25 of its 60 references that are in the map. First posted on arXiv 16 Sep 2022.
Builds on
25 of 60 references.
References · 25
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
- 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 254
- 2021End-to-end Interpretable Neural Motion Plannercited by 242
- 2019Algorithms for Verifying Deep Neural Networkscited by 221
- 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
- 2020DeepReach: A Deep Learning Approach to High-Dimensional Reachabilitycited by 91
- 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 84
- 2017Output Reachable Set Estimation and Verification for Multi-Layer Neural Networkscited by 80
- 2017How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Roboticscited by 59
- 2020Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programmingcited by 43
- 2020Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems with Deep Neural Network Componentscited by 36
13 more
- 2018Efficient Bayesian Inference of Sigmoidal Gaussian Cox Processescited by 17
- 2019Data-Driven Reachable Set Computation using Adaptive Gaussian Process Classification and Monte Carlo Methodscited by 14
- 2018Bridging the Gap Between Safety and Real-Time Performance in Receding-Horizon Trajectory Design for Mobile Robotscited by 11
- 2020Reachability Analysis for Feed-Forward Neural Networks using Face Latticescited by 11
- 2020Sampling-based Reachability Analysis: A Random Set Theory Approach with Adversarial Samplingcited by 11
- 2021Learning Density Distribution of Reachable States for Autonomous Systemscited by 11
- 2021Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllerscited by 10
- 2013Technical Report: Convex Optimization of Nonlinear Feedback Controllers via Occupation Measurescited by 8
- 2020PAC Model Checking of Black-Box Continuous-Time Dynamical Systemscited by 8
- 2021Data-Driven Set-Based Estimation using Matrix Zonotopes with Set Containment Guaranteescited by 6
- 2020State-Based Confidence Bounds for Data-Driven Stochastic Reachability Using Hilbert Space Embeddingscited by 4
- 2014Approximation of reachable sets using optimal control and support vector machinescited by 2
- 2019Optimal Safe Controller Synthesis: A Density Function Approachcited by 2
Built on by
Citing papers per year: 2022: 1.
1 paper.