Papers for

robotic engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Humanoid robots use force commands to handle heavy objects

Ctrl-F: Force as an Interface for Humanoid Loco-Manipulation

Abstract: Humanoid motion tracking has scaled to general policies that reproduce diverse human motion, but the resulting behavior is in free-space: the tracker knows where the body should be, not how it should interact with the environment. Other work makes the object part of the objective, yet abstracts that interaction to contact or geometry, which leaves the demanding cases under-explored. We argue that force is a natural command channel between motion imitation and object interaction, one that specifies not just where to make contact but how hard. We present Ctrl-F, a hierarchical motion-force framework that augments motion tracking with an explicit force command, a 3-D force at each designated contact body such as a hand or a foot. The hierarchical framework comprises: (1) A unified motion-force controller tracks the reference motion while applying the commanded force to the world. (2) A high-level force planner that issues a force command online based on object state and proprioception observations. In simulation and on hardware, Ctrl-F completes loco-manipulation that demands large, sustained interaction force and adjusts its command online as the load changes, both out of reach of a force-blind tracker. On hardware, Ctrl-F demonstrates hand-based dragging, pushing, and lifting, as well as foot-based kicking, successfully manipulating boxes weighing up to 20kg in pushing and kicking tasks where the force-blind baseline fails, while adapting online to additional loads introduced mid-task.

Tue 3 NovRoboticsMachine Learning
The gist
Humanoid robots often copy human movements but usually do so without knowing how to physically interact with things, like how hard to push or pull. The authors created Ctrl-F, a system that adds force commands to the robot’s movements, telling it where and how hard to apply force when touching objects. This lets the robot perform tasks like dragging, pushing, lifting, and kicking objects that weigh up to 20 kilograms, adapting on the fly if the load changes. Their approach works both in simulations and in real robot tests, succeeding where systems without force feedback fail.
Open → 2611.05507v1

AI improves autonomous science in space laboratories and planets

AI for Science in Space: Orbital Laboratories, Planetary Fieldwork, and Embodied Autonomy

Abstract: Artificial intelligence for science (AI4S) is extending from interpretation of existing data to the design and execution of experiments. Space offers distinctive scientific opportunities while restricting physical support. Microgravity and extraterrestrial environments expose phenomena that terrestrial experiments cannot fully reproduce; finite samples, constrained resources, and limited opportunities for intervention complicate sustained investigation. This critical review examines orbital laboratories and planetary in situ science across biology, materials, fluid and thermal physics, and adaptive exploration. We distinguish learning from space-derived data, selecting scientific actions, executing them, and preserving experimental validity. Terrestrial self-driving laboratories provide complementary evidence on optimization, dedicated automation, robotic manipulation, and the support needed for unattended operation. The synthesis connects scientific gains already demonstrated by bounded AI systems to gaps in observation, executable actions, and continuity of valid evidence. Space robots can expand the attainable scope of autonomous science when necessary interventions exceed validated instrument capabilities and timely human support is unavailable. Their value must be established against dedicated mechanisms, redundancy, and human-supported operation. We develop a framework connecting sample history, scientific decisions, physical execution, and claim-specific validity. A worked orbital design, a planetary extension, and matched evaluation schemes separate the contributions of sensing, decision policies, and physical actions. The resulting agenda measures autonomy through valid scientific return, task coverage, intervention costs, and evidence integrity across complete campaigns.

Thu 29 OctRobotics
The gist
Doing experiments in space is very different from on Earth because there are many challenges like limited help, special environments, and fewer chances to fix problems. The authors look at how artificial intelligence can help run experiments independently in space labs and on planets. They explain how AI can learn from data, decide what to do next, carry out actions, and keep experiments reliable. Their work suggests ways to measure how well AI works for space science and shows how robots could help when people can't intervene quickly.
Open → 2610.39689v1

Coordi-pi improves robot dual-hand coordination for fine tasks

Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation

Abstract: Vision-language-action (VLA) models have shown strong potential for general-purpose robotic manipulation, but extending them to bimanual dexterous manipulation introduces a high-dimensional and structured action space. Existing bimanual VLA policies commonly concatenate right- and left-side arm--hand actions at each control timestep, leaving cross-hand interactions implicit within a single action vector. We introduce Coordi-$π$, a structured action representation for bimanual dexterous manipulation. Coordi-$π$ represents the right- and left-side arm--hand actions as individual action tokens and organizes them into an interleaved sequence, explicitly exposing the two sides within the action sequence. To explicitly encode hand identity and temporal synchronization in this interleaved representation, a learnable hand-identity embedding distinguishes the two sides, while sequence--control-timestep factorized rotary positional encoding (RoPE) separates sequence position from control timestep, allowing actions at the same control timestep to share a temporal coordinate while retaining distinct sequence positions. Across all five bimanual dexterous manipulation tasks in DexJoCo, Coordi-$π$ achieves state-of-the-art performance under both \textit{rand-obj} and \textit{rand-full}, improving the average success rate over $π_{0.5}$ from 31.9\% to 51.3\% and from 18.3\% to 32.3\%, respectively. Coordi-$π$ also consistently outperforms $π_{0.5}$ across four real-world bimanual dexterous manipulation tasks.

Wed 14 OctRobotics
The gist
Making robots use both hands together is very tricky because each hand can move in many ways and they need to work together smoothly. The authors created Coordi-$pi$, a new way to represent actions for both hands separately but in a coordinated sequence. This helps the robot understand and perform complex two-handed tasks better than before. Their method works well in tests both in simulation and the real world, improving success in tasks like picking and manipulating objects with both hands.
Open → 2610.19753v1

Robotic policies adapt online by learning from action outcomes

Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback

Abstract: While pretrained robotic policies exhibit impressive capabilities in controlled environments, unobserved physical properties and dynamics require these policies to rapidly adapt during deployment. Existing test-time adaptation methods typically rely on sparse scalar rewards, failing to exploit the rich geometric and dynamic feedback from the environment during physical interaction. To address this challenge, we propose SCOUT, a dynamics-aware meta-learning framework that enables manipulation policies to rapidly adapt by continuously revising their internal beliefs about environment dynamics. Our approach couples an action-prediction policy with a forward dynamics model via a shared belief latent space. During meta-training, an inner loop updates this shared belief latent by minimizing the dynamics prediction error against the observed action outcome, while the outer loop optimizes the network for action selection. At deployment, this structure allows the agent to infer and adapt to unknown physical dynamics on the fly. By updating its latent belief based on action-outcome mismatches, the policy automatically adapts without risking catastrophic forgetting. We demonstrate that SCOUT significantly accelerates online adaptation across simulated manipulation benchmarks and achieves robust sim-to-real transfer in the real world. Project webiste can be found here: https://liy1shu.github.io/SCOUT/

Mon 28 SeptRobotics
The gist
Robots that have learned to operate in controlled settings often struggle when new or unexpected things happen, like changes in the objects they handle. The authors propose SCOUT, a learning method that helps robots quickly adjust their understanding of how things work by watching the results of their own actions. This way, the robot doesn’t just rely on simple rewards but uses detailed feedback to update its expectations and improve performance during real-world tasks. The method was tested in simulations and with real robots, showing it helps them adapt faster and more reliably.
Open → 2609.36107v1

Efficient vision language control improves robot tasks with token caching

Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference

Abstract: Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive. Token caching provides a training-free, plug-and-play acceleration alternative. However, existing VLA caching does not fully exploit a key inductive bias of VLA models: text-vision synergy, wherein textual semantics guide the precise visual grounding of task-relevant regions. In particular, existing designs insufficiently account for head-wise reliability in attention aggregation and layer-wise stability in cache reuse. To address this, we propose Text-Vision Synergistic Token Caching (TVCache), a training-free framework for efficient VLA inference. TVCache filters attention heads based on text-vision information focus to improve task-relevant and physically consistent visual grounding. Concurrently, we introduce a reuse-layer selection mechanism guided by text-vision entropy differences to avoid caching unstable representations and improve cache resource allocation. Extensive experiments across four representative VLA models, two simulation benchmarks, and real-world robotic tasks demonstrate the effectiveness and generality of TVCache. At matched token-retention ratios, TVCache consistently improves task success over existing VLA caching with comparable computational cost. On OpenVLA-OFT, it improves average success by up to 14.5 percentage points over VLA-Cache at 12.5% retention while reducing FLOPs by 2.45x relative to full-token inference.

Mon 28 SeptComputer Vision and Pattern RecognitionRobotics
The gist
Robots that understand both pictures and words often need a lot of computing power to decide what to do. The authors found a way to make this faster without retraining the robot’s brain by saving and reusing certain important visual and text clues. Their method, called TVCache, picks the most helpful parts of the robot’s thought process to speed up decision-making, especially by focusing on how words and images work together. Tests showed robots using TVCache completed tasks more successfully and with less computing work.
Open → 2609.34319v1

Bioinspired estimator improves online tracking with partial sensor data

A bioinspired internal model-based online estimator for planar pursuit

Abstract: Bioinspired feedback controls for pursuit, tracking, and collective motion are often expressed in terms of the relative configuration between interacting agents. In practice, however, onboard sensors may not directly provide all quantities required for feedback control, necessitating estimation of unobserved quantities. This paper develops a bioinspired internal model-based estimator for reconstructing those quantities from partial sensory observations and known self-motion. State reconstruction is posed as an optimization problem that treats the relative kinematics as constraints and minimizes the disagreement between the internal model outputs and measurements from onboard sensors. Pontryagin's Maximum Principle is used to derive the necessary optimality conditions. A forward-backward algorithm is used to provide a numerical solution and a moving horizon formulation is employed for online implementation. The estimator is evaluated numerically against classical state estimators. Real-time implementation of the proposed framework on robotic hardware is demonstrated through two pursuit strategies.

Mon 21 SeptRobotics
The gist
Tracking and following moving targets often needs knowing relationships between agents, but sensors don’t always give all necessary information directly. The authors developed a way to estimate the missing information by combining a biological inspiration with a mathematical model that tries to best fit the available sensor data. They use advanced optimization techniques to solve this problem efficiently in real time. Their method works better than traditional state estimators and can be run live on robots to help them pursue targets more effectively.
Open → 2609.25470v1

Humanoid robot learns to swing across bars like primates

SwingBot: Learning Whole-Body Brachiation for Humanoid Robots

Abstract: Brachiation enables primates to move across overhead supports when ground paths are blocked, suggesting a complementary locomotion mode for robots operating in cluttered or hazardous environments. Bringing this capabil?ity to high-DoF humanoid robots is difficult because the controller must discover a long-horizon release-swing-capture sequence, coordinate alternating contacts with whole-body momentum, and act without reliable measurements of segment?relative displacement or hook-contact state. We present SwingBot, a learning framework for continuous humanoid brachiation with passive wrist hooks. Swing?Bot makes the task trainable by organizing learning around the structure of brachi?ation: biomimetic keyframes make rare release-swing-capture transitions reach?able during early exploration, and recurrent privileged-state estimation provides compact position and contact latents for deployment. Hardware experiments demonstrate continuous bar traversal and robustness to payload, external distur?bances and different bar spacings, showing that this formulation offers a practical route to whole-body robotic brachiation.

Wed 9 SeptRobotics
The gist
Moving through cluttered spaces can be hard for robots that walk on two legs. The authors developed SwingBot, a system that helps humanoid robots swing hand over hand, like monkeys on jungle gyms. Their approach breaks down this complex swinging motion into simpler steps and uses special learning to train the robot to keep its balance and grip. They tested SwingBot on real robots swinging through bars repeatedly, even with added weight and bumps, showing it can handle tricky movements.
Open → 2609.10283v1