Robots must often be able to move around and interact with objects in previously-unseen environments to be useful. And the interaction part is important; to do this, they must be able to perceive and interact with the world using onboard sensing.

Enter VisualMimic. Shaofeng Yin and Yanjie Ze show us how to use visual sim-to-real to train diverse loco-manipulation tasks, which can even handle diverse outdoor environments.

Learn more in Episode #48 of RoboPapers today, hosted by Michael Cho and Chris Paxton.

Abstract:

Humanoid loco-manipulation in unstructured environments demands tight integration of egocentric perception and whole-body control. However, existing approaches either depend on external motion capture systems or fail to generalize across diverse tasks. We introduce VisualMimic, a visual sim-to-real framework that unifies egocentric vision with hierarchical whole-body control for humanoid robots. VisualMimic combines a task-agnostic low-level keypoint tracker -- trained from human motion data via a teacher-student scheme -- with a task-specific high-level policy that generates keypoint commands from visual and proprioceptive input. To ensure stable training, we inject noise into the low-level policy and clip high-level actions using human motion statistics. VisualMimic enables zero-shot transfer of visuomotor policies trained in simulation to real humanoid robots, accomplishing a wide range of loco-manipulation tasks such as box lifting, pushing, football dribbling, and kicking. Beyond controlled laboratory settings, our policies also generalize robustly to outdoor environments. Videos are available at: this https URL .

Project Page: https://visualmimic.github.io/

ArXiV: https://arxiv.org/abs/2509.20322

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

For robots to be useful, they can’t just dance — they must be able to physically interact with the world around them. Unfortunately, the sorts of motion tracking policies you see performing dancing or martial arts are not really capable of the kind of precise, forceful interaction needed to perform useful interactions with the world.

Siheng and Yanjie join us to talk about ResMimic, their new paper which takes a general-purpose human motion-tracking policy and improves it with a residual policy to reliably interact with objects

To learn more, watch Episode #47 of RoboPapers, hosted by Michael Cho and Chris Paxton, today!

Abstract:

Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these policies lack the precision and object awareness required for loco-manipulation. To this end, we introduce ResMimic, a two-stage residual learning framework for precise and expressive humanoid control from human motion data. First, a GMT policy, trained on large-scale human-only motion, serves as a task-agnostic base for generating human-like whole-body movements. An efficient but precise residual policy is then learned to refine the GMT outputs to improve locomotion and incorporate object interaction. To further facilitate efficient training, we design (i) a point-cloud-based object tracking reward for smoother optimization, (ii) a contact reward that encourages accurate humanoid body-object interactions, and (iii) a curriculum-based virtual object controller to stabilize early training. We evaluate ResMimic in both simulation and on a real Unitree G1 humanoid. Results show substantial gains in task success, training efficiency, and robustness over strong baselines.

Project Page: https://resmimic.github.io/

ArXiV: https://www.arxiv.org/abs/2510.05070

Original post on X: https://x.com/SihengZhao/status/1975985531298476316

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

Improving robot's’ ability to learn from human demonstrations is key to getting better performance from them in a wide variety of tasks. Algorithmic improvements like consistency flow training and a new architecture which can leverage multimodal inputs, allows ManiFlow to substantially improve on prior work while also showing strong generalization to unseen environments and distractors. Ge Yan tells us more about how this works and how we can make imitation learning better.

Find out more on RoboPapers #46, with Michael Cho and Chris Paxton!

Abstract:

We introduces ManiFlow, a visuomotor imitation learning policy for general robot manipulation that generates precise, high-dimensional actions conditioned on diverse visual, language and proprioceptive inputs. We leverage flow matching with consistency training to enable high-quality dexterous action generation in just 1-2 inference steps. To handle diverse input modalities efficiently, we propose DiT-X, a diffusion transformer architecture with adaptive cross-attention and AdaLN-Zero conditioning that enables fine-grained feature interactions between action tokens and multi-modal observations. ManiFlow demonstrates consistent improvements across diverse simulation benchmarks and nearly doubles success rates on real-world tasks across single-arm, bimanual, and humanoid robot setups with increasing dexterity. The extensive evaluation further demonstrates the strong robustness and generalizability of ManiFlow to novel objects and background changes, and highlights its strong scaling capability with larger-scale datasets.

Project Page: https://maniflow-policy.github.io/

ArXiV Paper: https://www.arxiv.org/pdf/2509.01819

Thread on X

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

Just collecting manipulation data isn’t enough for robots - they need to be able to move around in the world, which has a whole different set of challenges from pure manipulation. And bringing navigation and manipulation together in a single framework is even more challenging.

Enter HERMES, from Zhecheng Yuan and Tianming Wei. This is a four-stage process in which human videos are used to set up an RL sim-to-real training pipeline in order to overcome differences between robot and human kinematics, and used together with a navigation foundation model to move around in a variety of environments.

To learn more, join us as Zhecheng Yuan and Tianming Wei tell us about how they built their system to perform mobile dexterous manipulation from human videos in a variety of environments.

Watch Episode #45 of RoboPapers today, hosted by Michael Cho and Chris Paxton!

Abstract:

Leveraging human motion data to impart robots with versatile manipulation skills has emerged as a promising paradigm in robotic manipulation. Nevertheless, translating multi-source human hand motions into feasible robot behaviors remains challenging, particularly for robots equipped with multi-fingered dexterous hands characterized by complex, high-dimensional action spaces. Moreover, existing approaches often struggle to produce policies capable of adapting to diverse environmental conditions. In this paper, we introduce HERMES, a human-to-robot learning framework for mobile bimanual dexterous manipulation. First, HERMES formulates a unified reinforcement learning approach capable of seamlessly transforming heterogeneous human hand motions from multiple sources into physically plausible robotic behaviors. Subsequently, to mitigate the sim2real gap, we devise an end-to-end, depth image-based sim2real transfer method for improved generalization to real-world scenarios. Furthermore, to enable autonomous operation in varied and unstructured environments, we augment the navigation foundation model with a closed-loop Perspective-n-Point (PnP) localization mechanism, ensuring precise alignment of visual goals and effectively bridging autonomous navigation and dexterous manipulation. Extensive experimental results demonstrate that HERMES consistently exhibits generalizable behaviors across diverse, in-the-wild scenarios, successfully performing numerous complex mobile bimanual dexterous manipulation tasks

Project Page: https://gemcollector.github.io/HERMES/

ArXiV: https://arxiv.org/abs/2508.20085

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

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning?

Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings.

To find out more, watch episode #44 of RoboPapers with Michael Cho and Chris Paxton now!

Abstract:

Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract symbolic world models that facilitate zero-shot generalization to novel goals via planning. A critical component of such models is the set of symbolic predicates that define properties of and relationships between objects. In this work, we leverage pretrained vision language models (VLMs) to propose a large set of visual predicates potentially relevant for decision-making, and to evaluate those predicates directly from camera images. At training time, we pass the proposed predicates and demonstrations into an optimization-based model-learning algorithm to obtain an abstract symbolic world model that is defined in terms of a compact subset of the proposed predicates. At test time, given a novel goal in a novel setting, we use the VLM to construct a symbolic description of the current world state, and then use a search-based planning algorithm to find a sequence of low-level skills that achieves the goal. We demonstrate empirically across experiments in both simulation and the real world that our method can generalize aggressively, applying its learned world model to solve problems with a wide variety of object types, arrangements, numbers of objects, and visual backgrounds, as well as novel goals and much longer horizons than those seen at training time.

Project Page

ArXiV

Thread on X

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

Walking robots can do all kinds of exciting things like dancing, running, and martial arts — but for them to be useful, they must be able to use their legs to handle terrain, to move over obstacles not just around them. So, how can we train walking policies for legged robots that are useful?

Unlike with manipulation, these policies are trained with end-to-end, sim-to-real reinforcement learning, using attention. Turns out maybe “attention is all you need” also applies to locomotion. Chong Zhang joins us to explain more.

Watch Episode #43 of RoboPapers, hosted by Michael Cho and Chris Paxton, now, to find out more.

Abstract:

Dynamic locomotion of legged robots is a critical yet challenging topic in expanding the operational range of mobile robots. It requires precise planning when possible footholds are sparse, robustness against uncertainties and disturbances, and generalizability across diverse terrains. Although traditional model-based controllers excel at planning on complex terrains, they struggle with real-world uncertainties. Learning-based controllers offer robustness to such uncertainties but often lack precision on terrains with sparse steppable areas. Hybrid methods achieve enhanced robustness on sparse terrains by combining both methods but are computationally demanding and constrained by the inherent limitations of model-based planners. To achieve generalized legged locomotion on diverse terrains while preserving the robustness of learning-based controllers, this paper proposes an attention-based map encoding conditioned on robot proprioception, which is trained as part of the controller using reinforcement learning. We show that the network learns to focus on steppable areas for future footholds when the robot dynamically navigates diverse and challenging terrains. We synthesized behaviors that exhibited robustness against uncertainties while enabling precise and agile traversal of sparse terrains. In addition, our method offers a way to interpret the topographical perception of a neural network. We have trained two controllers for a 12-degrees-of-freedom quadrupedal robot and a 23-degrees-of-freedom humanoid robot and tested the resulting controllers in the real world under various challenging indoor and outdoor scenarios, including ones unseen during training.

Paper in Science Robotics

ArXiV

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

With enough data, robots and AI can learn “world models” that let them predict the results of their actions. These models are a way to learn how embodied AI agents can perform a wide variety of useful tasks — but they require a huge amount of data.

The team at General Intuition has a solution: use data from video games! Games teach movement, problem solving, and complex spatial reasoning, and they come in a staggering diversity of forms, covering a wide variety of problems. What’s more, the captured data is high-quality, without the noise or annotation error that can come from

We sat down with Pim and Adam from the General Intuition team to learn more about their history, their plans, and their philosophy.

Abstract:

World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequences of discrete latent variables to model environment dynamics. However, this compression into a compact discrete representation may ignore visual details that are important for reinforcement learning. Concurrently, diffusion models have become a dominant approach for image generation, challenging well-established methods modeling discrete latents. Motivated by this paradigm shift, we introduce DIAMOND (DIffusion As a Model Of eNvironment Dreams), a reinforcement learning agent trained in a diffusion world model. We analyze the key design choices that are required to make diffusion suitable for world modeling, and demonstrate how improved visual details can lead to improved agent performance. DIAMOND achieves a mean human normalized score of 1.46 on the competitive Atari 100k benchmark; a new best for agents trained entirely within a world model. We further demonstrate that DIAMOND’s diffusion world model can stand alone as an interactive neural game engine by training on static Counter-Strike: Global Offensive gameplay. To foster future research on diffusion for world modeling, we release our code, agents and playable world models at https://github.com/eloialonso/diamond.

Project Page

General Intuition

General Intuition is Hiring: https://jobs.ashbyhq.com/medal

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

How can we make a humanoid robot play table tennis? The robot must hit a moving ball and return it over and over again, requiring precise whole-body control over again. Zhi Su tells us about how he developed a hierarchical approach for planning an whole body control that lets people play this game with a humanoid robot.

Watch Episode #41 of RoboPapers with Michael Cho and Chris Paxton now!

Abstract:

Humanoid robots have recently achieved impressive progress in locomotion and whole-body control, yet they remain constrained in tasks that demand rapid interaction with dynamic environments through manipulation. Table tennis exemplifies such a challenge: with ball speeds exceeding 5 m/s, players must perceive, predict, and act within sub-second reaction times, requiring both agility and precision. To address this, we present a hierarchical framework for humanoid table tennis that integrates a model-based planner for ball trajectory prediction and racket target planning with a reinforcement learning-based whole-body controller. The planner determines striking position, velocity and timing, while the controller generates coordinated arm and leg motions that mimic human strikes and maintain stability and agility across consecutive rallies. Moreover, to encourage natural movements, human motion references are incorporated during training. We validate our system on a general-purpose humanoid robot, achieving up to 106 consecutive shots with a human opponent and sustained exchanges against another humanoid. These results demonstrate real-world humanoid table tennis with sub-second reactive control, marking a step toward agile and interactive humanoid behaviors.

Project Page

ArXiV

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

How can we build robotic hands with truly superhuman dexterity? Daxo Robotics is developing a unique tendon-driven soft robot hand, which aims to be tougher and more capable than a traditional humanoid hand. Each finger consists of many different tendons, which act in concert to move or manipulate.

This is a special episode of RoboPapers where, instead of talking about a scientific paper, we talk to Tom Zhang, founder of Daxo Robotics, in order to learn both about his background and about how this one-of-a-kind robot hand design works.

Watch Episode #40 of RoboPapers with Michael Cho and Chris Paxton now!

Daxo Robotics website

Follow Tom on X

Watch this episode on YouTube

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

Reasoning models have massively expanded what LLMs are capable of, but this hasn’t necessarily applied to robotics. Perhaps this is in part because robots need to reason over space, not just words and symbols; so the robotics version of a reasoning model would need to think in 3D. That’s the idea behind MolmoAct, an “Action Reasoning Model” which generates spatial plans in order to predict precise low-level robot actions. Jason Lee, Haoquan Fang, and Jiafei Duan told us more about their work.

Watch Episode #39 of RoboPapers, with Michael Cho and Chris Paxton, now!

Abstract:

Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of robotic foundation models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1.5; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: this https URL

Paper

Project website

Original post on X

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