mlsanityData to 14 Oct 2026

VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain

arXiv 2409.17469 ↗First posted 26 Sep 2024cs.ROcited by 3

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

Reinforcement Learning (RL) has the potential to enable extreme off-road mobility by circumventing complex kinodynamic modeling, planning, and control by simulated end-to-end trial-and-error learning experiences. However, most RL methods are sample-inefficient when training in a large amount of manually designed simulation environments and struggle at generalizing to the real world. To address these issues, we introduce VertiSelector (VS), an automatic curriculum learning framework designed to enhance learning efficiency and generalization by selectively sampling training terrain. VS prioritizes vertically challenging terrain with higher Temporal Difference (TD) errors when revisited, thereby allowing robots to learn at the edge of their evolving capabilities. By dynamically adjusting the sampling focus, VS significantly boosts sample efficiency and generalization within the VW-Chrono simulator built on the Chrono multi-physics engine. Furthermore, we provide simulation and physical results using VS on a Verti-4-Wheeler platform. These results demonstrate that VS can achieve 23.08% improvement in terms of success rate by efficiently sampling during training and robustly generalizing to the real world.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 39 of its 66 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

39 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Reinforcement Learning for Wheeled Mobility on Vertically Challenging Terrain4 Sep

Other references · 38

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2017Hindsight Experience Replaycited by 1,136
  5. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  6. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  7. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  8. 2020Prioritized Level Replaycited by 198
  9. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 119
  10. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 81
  11. 2014Curriculum Learning of Multiple Taskscited by 66
  12. 2019Increasing Generality in Machine Learning through Procedural Content Generationcited by 59
26 more
  1. 2020Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Surveycited by 58
  2. 2022Elevation Mapping for Locomotion and Navigation using GPUcited by 43
  3. 2018Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Modelcited by 35
  4. 2023V-STRONG: Visual Self-Supervised Traversability Learning for Off-road Navigationcited by 32
  5. 2023TerrainNet: Visual Modeling of Complex Terrain for High-speed, Off-road Navigationcited by 30
  6. 2022Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigationcited by 29
  7. 2022How Does It Feel? Self-Supervised Costmap Learning for Off-Road Vehicle Traversabilitycited by 27
  8. 2023Learning Off-Road Terrain Traversability with Self-Supervisions Onlycited by 27
  9. 2021Learning Inverse Kinodynamics for Accurate High-Speed Off-Road Navigation on Unstructured Terraincited by 25
  10. 2022VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamicscited by 21
  11. 2023EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomycited by 21
  12. 2020APPLD: Adaptive Planner Parameter Learning from Demonstrationcited by 20
  13. 2021OFFSEG: A Semantic Segmentation Framework For Off-Road Drivingcited by 20
  14. 2021APPL: Adaptive Planner Parameter Learningcited by 20
  15. 2022Risk-Aware Off-Road Navigation via a Learned Speed Distribution Mapcited by 20
  16. 2020APPLI: Adaptive Planner Parameter Learning From Interventionscited by 19
  17. 2023Toward Wheeled Mobility on Vertically Challenging Terrain: Platforms, Datasets, and Algorithmscited by 19
  18. 2020APPLR: Adaptive Planner Parameter Learning from Reinforcementcited by 16
  19. 2021APPLE: Adaptive Planner Parameter Learning from Evaluative Feedbackcited by 16
  20. 2022High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimizationcited by 11
  21. 2023Learning to Model and Plan for Wheeled Mobility on Vertically Challenging Terraincited by 11
  22. 2021Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environmentscited by 8
  23. 2023PIAug -- Physics Informed Augmentation for Learning Vehicle Dynamics for Off-Road Navigationcited by 8
  24. 2024Terrain-Attentive Learning for Efficient 6-DoF Kinodynamic Modeling on Vertically Challenging Terraincited by 7
  25. 2018A Data-Driven Approach for Autonomous Motion Planning and Control in Off-Road Driving Scenarioscited by 3
  26. 2018Estimating Achievable Range of Ground Robots Operating on Single Battery Discharge for Operational Efficacy Ameliorationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learningcited by 4
  2. 2025Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learningcited by 1
  3. 2026Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terraincited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Scaling Rough Terrain Locomotion with Automatic Curriculum Reinforcement Learning
  2. 2026Verti-WM: A Physics-Aided Exteroceptive World Model for Off-Road Reinforcement Learning
  3. 2025Verti-Bench: A General and Scalable Off-Road Mobility Benchmark for Vertically Challenging Terrain
  4. 2025Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility
  5. 2026Curriculum Generation under Structured Parametric Environments for Robust Navigation Policies
  6. 2026Scaling Curriculum Learning For Autonomous Driving
  7. 2025Learning Terrain-Specialized Policies for Adaptive Locomotion in Challenging Environments
  8. 2024Grounded Curriculum Learning