roto 2.0: The Robot Tactile Olympiad
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (textttroto 2.0), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 18 of its 20 references that are in the map. First posted on arXiv 20 May 2026.
Builds on
18 of 20 references.
Closest ancestors · 1
Same direction, newest first
Other references · 17
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2018Learning Dexterous In-Hand Manipulationcited by 687
- 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
- 2021A System for General In-Hand Object Re-Orientationcited by 165
- 2022In-Hand Object Rotation via Rapid Motor Adaptationcited by 118
- 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 112
- 2023General In-Hand Object Rotation with Vision and Touchcited by 99
- 2023Rotating without Seeing: Towards In-hand Dexterity through Touchcited by 84
- 2023Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensingcited by 56
- 2022skrl: Modular and Flexible Library for Reinforcement Learningcited by 49
- 2023Neural feels with neural fields: Visuo-tactile perception for in-hand manipulationcited by 28
- 2025Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuningcited by 26
5 more
- 2024AnyRotate: Gravity-Invariant In-Hand Object Rotation with Sim-to-Real Touchcited by 21
- 2022Learning Purely Tactile In-Hand Manipulation with a Torque-Controlled Handcited by 20
- 2022Tactile Gym 2.0: Sim-to-real Deep Reinforcement Learning for Comparing Low-cost High-Resolution Robot Touchcited by 18
- 2023TacGNN:Learning Tactile-based In-hand Manipulation with a Blind Robotcited by 11
- 2023Estimator-Coupled Reinforcement Learning for Robust Purely Tactile In-Hand Manipulationcited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024Sim2Real Manipulation on Unknown Objects with Tactile-based Reinforcement Learning
- 2026OpenViTac: Learning and Benchmarking Visuo-Tactile Policies in a Unified Sim-and-Real Framework ↗
- 2026Tactile-Guided Robot Learning: From Representation Learning to Foundation Models ↗
- 2024Data-Driven Optimization of Tactile Sensor Configurations for Efficient Dexterous Manipulation
- 2024Learning In-Hand Translation Using Tactile Skin With Shear and Normal Force Sensing
- 2026TouchWorld: A Predictive and Reactive Tactile Foundation Model for Dexterous Manipulation
- 2026TACO: TActile World Model as a Self-COrrector for Scalable Robot Policy Post-Training
- 2025The Role of Tactile Sensing for Learning Reach and Grasp