Ep#88: DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation

Ep#88: DexSkin: High-Coverage Conformable Robotic Skin for Learning Contact-Rich Manipulation

Human skin plays an important role in how we interact with the world and robustly manipulate objects. It’s not just important when we can’t see things with out eyes, but when we want to pick up something heavy, or apply a very specific amount of force. So, it makes sense to want to give robots skin. Enter DexSkin: a soft, deformable electronic skin which can be applied across different surfaces and used to cover robot hands or fingers. Suzannah Wistreich and Baiyu Shi talk to us about their work building DexSkin, showing how it’s useful for policy learning, including online reinforcement learning, and how it' can be calibrated and policies transferred across sensors. They also open sourced their code and methods for building the sensors. To learn more, watch Episode #88 of RoboPapers now, hosted by Chris Paxton and Jiafei Duan! Abstract Human skin provides a rich tactile sensing stream, localizing intentional and unintentional contact events over a large and contoured region. Replicating these tactile sensing capabilities for dexterous robotic manipulation systems remains a longstanding challenge. In this work, we take a step towards this goal by introducing DexSkin. DexSkin is a soft, conformable capacitive electronic skin that enables sensitive, localized, and calibratable tactile sensing, and can be tailored to varying geometries. We demonstrate its efficacy for learning downstream robotic manipulation by sensorizing a pair of parallel jaw gripper fingers, providing tactile coverage across almost the entire finger surfaces. We empirically evaluate DexSkin's capabilities in learning challenging manipulation tasks that require sensing coverage across the entire surface of the fingers, such as reorienting objects in hand and wrapping elastic bands around boxes, in a learning-from-demonstration framework. We then show that, critically for data-driven approaches, DexSkin can be calibrated to enable model transfer across sensor instances, and demonstrate its applicability to online reinforcement learning on real robots. Our results highlight DexSkin's suitability and practicality for learning real-world, contact-rich manipulation. Please see our project webpage for videos and visualizations: this https URL [https://dex-skin.github.io/]. Learn More ArXiV: https://arxiv.org/abs/2509.18830 [https://arxiv.org/abs/2509.18830] Project Page: https://dex-skin.github.io/ [https://dex-skin.github.io/] Github: https://github.com/sdwistreich/dexskin [https://github.com/sdwistreich/dexskin] Datasets: https://huggingface.co/datasets/swistreich/dexskin [https://huggingface.co/datasets/swistreich/dexskin] This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit robopapers.substack.com [https://robopapers.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Ep#87: MolmoAct 2: An open foundation for robots that work in the real world

There are few truly open models in the world, including both weights and data. However, these models are crucial for research and development of new systems — they help us learn which data is important and help develop new capabilities for deploying robots in the real world. MolmoAct2 provides a foundation for open research into robotics. It is associated with its own open dataset, an open-data action tokenizer, and a reasoning variant which predicts depth tokens. And people have actually been using it across the community, running experiments in their own labs or homes. Haoquan Fang and Jiafei Duan tell us more. Watch Episode 87 of RoboPapers, with Michael Cho and Chris Paxton, now! Abstract Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today’s systems fall short for real-world deployment. Frontier models are closed; open-weight alternatives are tied to expensive hardware; reasoning-augmented policies pay prohibitive latency for their grounding; and fine-tuned success rates remain below the threshold for dependable use. We present MolmoAct2, a fully open action reasoning model built for practical deployment, advancing its predecessor, MolmoAct along five axes. (1) MolmoAct2 is built on top of our new Molmo2-ER, a VLM backbone specialized for spatial and embodied reasoning, trained on a 3.3M-sample corpus with a specialize-then-rehearse recipe. (2) We release three new robot datasets spanning low-to-medium cost platforms: MolmoAct2-BimanualYAM Dataset, 720 hours of teleoperated bimanual trajectories that constitute the largest open bimanual dataset to date; MolmoAct2-DROID Dataset, a quality-filtered Franka subset of DROID; and MolmoAct2-SO100/101 Dataset, a quality-filtered SO-100/101 subset. (3) We train and release MolmoAct2-FAST Tokenizer, an open-weight, open-data action tokenizer trained on millions of trajectories across five embodiments. (4) We design a new VLA architecture to graft the discrete-token VLM into the flow-matching continuous-action expert via per-layer key-value (KV) conditioning. (5) we propose MolmoAct2-Think, an adaptive-depth reasoning variant that re-predicts depth tokens only for scene regions that change between timesteps, retaining geometric grounding at a fraction of prior latency. In the most extensive empirical study of any open VLA to date, spanning 7 simulation and real-world benchmarks, MolmoAct2 outperforms strong baselines including π0.5, while Molmo2-ER surpasses GPT-5 and Gemini Robotics ER-1.5 across 13 embodied-reasoning benchmarks. We release model weights, training code, and complete training data. Learn More Project page: https://allenai.org/blog/molmoact2 [https://allenai.org/blog/molmoact2] Code: https://github.com/allenai/molmoact2 [https://github.com/allenai/molmoact2] ArXiV: https://arxiv.org/pdf/2605.02881v1 [https://arxiv.org/pdf/2605.02881v1] And check out our episode on the original MolmoAct: This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit robopapers.substack.com [https://robopapers.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Ep#86: RISE: Self-Improving Robot Policy with Compositional World Model

Robot policies must be both reliable and highly capable to be useful; the best way to achieve this level of performance is with reinforcement learning. However, for reinforcement learning you are usually stuck between two difficult options: reinforcement in the real world is often risky and expensive, while reinforcement learning in a traditional simulator takes a lot of engineering work and has a persistent sim-to-real gap. What if instead you could train your robot purely in a world model? RISE by Jiazhi Yang et al [https://x.com/jiazhi_yang2024]. uses a compositional world model to predict the future and evaluate progress. This allows for a self-improving pipeline, which learns a world model from real data and then learns how the robot should perform different tasks. This pipeline results in a data-driven way to improve policy performance from real data but without real-world reinforcement learning. Watch Episode #86 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more! Abstract Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic manipulation tasks, where minor execution deviations can compound into failures. While reinforcement learning (RL) offers a principled path to robustness, on-policy RL in the physical world is constrained by safety risk, hardware cost, and environment reset. To bridge this gap, we present RISE, a scalable framework of robotic reinforcement learning via imagination. At its core is a Compositional World Model that (i) predicts multi-view future via a controllable dynamics model, and (ii) evaluates imagined outcomes with a progress value model, producing informative advantages for the policy improvement. Such compositional design allows state and value to be tailored by best-suited yet distinct architectures and objectives. These components are integrated into a closed-loop self-improving pipeline that continuously generates imaginary rollouts, estimates advantages, and updates the policy in imaginary space without costly physical interaction. Across three challenging real-world tasks, RISE yields significant improvement over prior art, with more than +35% absolute performance increase in dynamic brick sorting, +45% for backpack packing, and +35% for box closing, respectively. Learn More Project Page: https://opendrivelab.com/RISE/ [https://opendrivelab.com/RISE/] ArXiV: https://arxiv.org/abs/2602.11075 [https://arxiv.org/abs/2602.11075] This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit robopapers.substack.com [https://robopapers.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Ep#85: Tutor Intelligence

Collecting robot data at scale is key to deploying working manipulation policies, and the team from Tutor Intelligence is here to tell us about how to accomplish it. Their new announcement: a massive, 100-robot “data factory,” with a behind-the-scenes look at how to build a teleoperation platform and how to make robots and policies that are useful for their customers. Tutor Intelligence is a full-stack robotics company: they build robot arms, they sell robot arms, they write the software and they train neural networks. Josh Gruenstein [https://x.com/joshgruenstein], Jesse Michel [https://x.com/JesseMMichel], Shiraz [https://x.com/shirazkn] Khan, and Joe McCalmon join us to tell us more about how they scale both teleop data and human interventions from their teleoperators in order to train the policies they need. Watch Episode #85 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more! Learn More Blog post: https://tutorintelligence.com/blog/building-a-100-robot-data-factory-toward-factory-ready-ai [https://tutorintelligence.com/blog/building-a-100-robot-data-factory-toward-factory-ready-ai] This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit robopapers.substack.com [https://robopapers.substack.com?utm_medium=podcast&utm_campaign=CTA_1]

Ep#84: Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

Learning robust, general-purpose reward functions for robotics unlocks many potential applications, like on-robot reinforcement learning or dataset validation. However, there’s a question of how to actually train such reward functions. Training success/failure prediction leads to ambiguous signals partway through a demonstration — it’s hard to measure progress — making the method unsuitable for reinforcement learning, among other things. Predicting progress, on the other hand, does not give a good way of using failure data. So why not do both? Robometer combines both progress and preference supervision, resulting in a stable, scalable, and highly general reward learning approach. Anthony Liang, Yigit Korkmaz, and Jesse Zhang join us to tell us more. Watch Episode #84 of RoboPapers, with Chris Paxton and Jiafei Duan, to learn more! Abstract General-purpose robot reward models are typically trained to predict absolute task progress from expert demonstrations, providing only local, frame-level supervision. While effective for expert demonstrations, this paradigm scales poorly to large-scale robotics datasets where failed and suboptimal trajectories are abundant and assigning dense progress labels is ambiguous. We introduce Robometer, a scalable reward modeling framework that combines intra-trajectory progress supervision with inter-trajectory preference supervision. Robometer is trained with a dual objective: a frame-level progress loss that anchors reward magnitude on expert data, and a trajectory-comparison preference loss that imposes global ordering constraints across trajectories of the same task, enabling effective learning from both real and augmented failed trajectories. To support this formulation at scale, we curate RBM-1M, a reward-learning dataset comprising over one million trajectories spanning diverse robot embodiments and tasks, including substantial suboptimal and failure data. Across benchmarks and real-world evaluations, Robometer learns more generalizable reward functions than prior methods and improves robot learning performance across a diverse set of downstream applications. Code, model weights, and videos at this https URL [https://robometer.github.io/]. Learn More Project page: https://robometer.github.io/ [https://robometer.github.io/] ArXiV: https://arxiv.org/abs/2603.02115 [https://arxiv.org/abs/2603.02115] Code on Github: https://github.com/robometer/robometer [https://github.com/robometer/robometer] This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit robopapers.substack.com [https://robopapers.substack.com?utm_medium=podcast&utm_campaign=CTA_1]