MMD-OPT : Maximum Mean Discrepancy Based Sample Efficient Collision Risk Minimization for Autonomous Driving
Not on the map. Why?
Abstract (arXiv)
We propose MMD-OPT: a sample-efficient approach for minimizing the risk of collision under arbitrary prediction distribution of the dynamic obstacles. MMD-OPT is based on embedding distribution in Reproducing Kernel Hilbert Space (RKHS) and the associated Maximum Mean Discrepancy (MMD). We show how these two concepts can be used to define a sample efficient surrogate for collision risk estimate. We perform extensive simulations to validate the effectiveness of MMD-OPT on both synthetic and real-world datasets. Importantly, we show that trajectory optimization with our MMD-based collision risk surrogate leads to safer trajectories at low sample regimes than popular alternatives based on Conditional Value at Risk (CVaR).
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 12 Dec 2024.
Builds on
28 of 51 references.
References · 28
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
- 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 360
- 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
- 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
- 2021Principled Simplicial Neural Networks for Trajectory Predictioncited by 77
- 2021STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulationcited by 46
- 2022DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehiclescited by 36
- 2020Pedestrian Trajectory Prediction with Convolutional Neural Networkscited by 21
- 2013The Scenario Approach for Stochastic Model Predictive Control with Bounds on Closed-Loop Constraint Violationscited by 19
- 2019Safe Trajectory Generation for Complex Urban Environments Using Spatio-temporal Semantic Corridorcited by 16
- 2020Optimization-Based Hierarchical Motion Planning for Autonomous Racingcited by 11
16 more
- 2022Model- and Acceleration-based Pursuit Controller for High-Performance Autonomous Racingcited by 11
- 2024RACP: Risk-Aware Contingency Planning with Multi-Modal Predictionscited by 10
- 2020A Real-Time Approach for Chance-Constrained Motion Planning with Dynamic Obstaclescited by 9
- 2021Multi-Modal Model Predictive Control through Batch Non-Holonomic Trajectory Optimization: Application to Highway Drivingcited by 9
- 2020Provably Safe Trajectory Optimization in the Presence of Uncertain Convex Obstaclescited by 8
- 2022Maximum Mean Discrepancy Distributionally Robust Nonlinear Chance-Constrained Optimization with Finite-Sample Guaranteecited by 6
- 2022Risk-Aware Model Predictive Path Integral Control Using Conditional Value-at-Riskcited by 5
- 2023Risk-Averse Trajectory Optimization via Sample Average Approximationcited by 4
- 2023Covariance Steering for Uncertain Contact-rich Systemscited by 3
- 2018Solving Chance Constrained Optimization under Non-Parametric Uncertainty Through Hilbert Space Embeddingcited by 2
- 2020Safe Motion Planning for Autonomous Driving using an Adversarial Road Modelcited by 2
- 2016Consistent Kernel Mean Estimation for Functions of Random Variablescited by 1
- 2020A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Controlcited by 1
- 2021Safe Motion Planning against Multimodal Distributions based on a Scenario Approachcited by 1
- 2021CCO-VOXEL: Chance Constrained Optimization over Uncertain Voxel-Grid Representation for Safe Trajectory Planningcited by 1
- 2023Hilbert Space Embedding-based Trajectory Optimization for Multi-Modal Uncertain Obstacle Trajectory Predictioncited by 1
Built on by
Not cited yet.