mlsanityData to 7 Oct 2026

RAP: Risk-Aware Prediction for Robust Planning

arXiv 2210.01368 ↗First posted 4 Oct 2022cs.LG cs.ROcited by 12

Not on the map. Why?

Abstract (arXiv)

Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-estimated by finite-sampling approximations of probabilistic motion forecasts. This can lead to overconfident and unsafe robot behavior, even with robust planners. Instead of assuming full prediction coverage that robust planners require, we propose to make prediction itself risk-aware. We introduce a new prediction objective to learn a risk-biased distribution over trajectories, so that risk evaluation simplifies to an expected cost estimation under this biased distribution. This reduces the sample complexity of the risk estimation during online planning, which is needed for safe real-time performance. Evaluation results in a didactic simulation environment and on a real-world dataset demonstrate the effectiveness of our approach. The code and a demo are available.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 46 of its 79 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

46 of 79 references.

References · 46

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  3. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  4. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  5. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  6. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  7. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  8. 2021MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Predictioncited by 246
  9. 2021End-to-end Interpretable Neural Motion Plannercited by 240
  10. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  11. 2020DLow: Diversifying Latent Flows for Diverse Human Motion Predictioncited by 184
  12. 2015Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approachcited by 162
34 more
  1. 2021GOHOME: Graph-Oriented Heatmap Output for future Motion Estimationcited by 146
  2. 2013Risk-sensitive Reinforcement Learningcited by 129
  3. 2021HOME: Heatmap Output for future Motion Estimationcited by 122
  4. 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
  5. 2021THOMAS: Trajectory Heatmap Output with learned Multi-Agent Samplingcited by 101
  6. 2018Baidu Apollo EM Motion Plannercited by 99
  7. 2014Algorithms for CVaR Optimization in MDPscited by 98
  8. 2021LookOut: Diverse Multi-Future Prediction and Planning for Self-Drivingcited by 96
  9. 2019Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecastingcited by 87
  10. 2019Diverse Trajectory Forecasting with Determinantal Point Processescited by 80
  11. 2020What-If Motion Prediction for Autonomous Drivingcited by 80
  12. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  13. 2019Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANscited by 78
  14. 2018Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMscited by 77
  15. 2018Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulationcited by 76
  16. 2017How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Roboticscited by 57
  17. 2018Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objectivecited by 56
  18. 2017Multimodal Probabilistic Model-Based Planning for Human-Robot Interactioncited by 50
  19. 2019DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Samplingcited by 40
  20. 2021Vehicle trajectory prediction works, but not everywherecited by 39
  21. 2021Divide-and-Conquer for Lane-Aware Diverse Trajectory Predictioncited by 37
  22. 2020When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humanscited by 34
  23. 2020MATS: An Interpretable Trajectory Forecasting Representation for Planning and Controlcited by 30
  24. 2020Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interactioncited by 21
  25. 2022Control-Aware Prediction Objectives for Autonomous Drivingcited by 18
  26. 2021Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigationcited by 13
  27. 2021Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal controlcited by 12
  28. 2020FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesiscited by 10
  29. 2019Interpretable Modelling of Driving Behaviors in Interactive Driving Scenarios based on Cumulative Prospect Theorycited by 5
  30. 2019Kinematic Single Vehicle Trajectory Prediction Baselines and Applications with the NGSIM Datasetcited by 4
  31. 2021Limits of Probabilistic Safety Guarantees when Considering Human Uncertaintycited by 4
  32. 2019On the Convergence of the Iterative Linear Exponential Quadratic Gaussian Algorithm to Stationary Pointscited by 3
  33. 2020Risk-Aware Decision Making in Service Robots to Minimize Risk of Patient Falls in Hospitalscited by 3
  34. 2018Real-time Prediction of Intermediate-Horizon Automotive Collision Riskcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 1; 2026: 1.

12 papers.

  1. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversariescited by 36
  2. 2023Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?cited by 22
  3. 2024The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learningcited by 11
  4. 2023Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomycited by 9
  5. 2024JointMotion: Joint Self-Supervision for Joint Motion Predictioncited by 7
  6. 2024Generative AI Agents in Autonomous Machines: A Safety Perspectivecited by 7
  7. 2024SceneMotion: From Agent-Centric Embeddings to Scene-Wide Forecastscited by 4
  8. 2024Mixed Strategy Nash Equilibrium for Crowd Navigationcited by 3
  9. 2024Risk-aware Trajectory Prediction by Incorporating Spatio-temporal Traffic Interaction Analysiscited by 3
  10. 2024Robust Stochastic Shortest-Path Planning via Risk-Sensitive Incremental Samplingcited by 0
  11. 2025Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictionscited by 0
  12. 2026One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulationcited by 0