Robotics & Embodied AI - Weekly Roundup

Results show that fingertip-aligned visual force representations can be effectively used for force-aware conditioning in VLA-based dexterous hand manipulation.

Fisheye-VLA is presented, a visual interface that brings these capabilities together using a single passive fisheye, and demonstrates that a single fisheye can support these manipulation tasks without physical wrist cameras.

MotionForge is introduced, the first large- scale simulation benchmark and data-generation pipeline tailored to jointly evaluate domain shifts and long-horizon interaction in dynamic manipulation, exposing a critical gap between current policy capabilities and the requirements of robust long- horizon manipulation of dynamic objects under domain shifts.

An end-to-end pipeline that captures motion in the operating room and uses it to train a surgical robot policy, validated on live animals, and shows that demonstrations recorded from a surgeon's own instruments are sufficient to train, select and deploy a bimanual surgical policy in vivo.

Geometry-Change VLA (GC-VLA), which learns to predict multiview future-current geometry-change tokens from current observations and applies Geometry-Conditioned Residual Flow (GCRF), using a binary intervention router and a single bounded residual velocity policy learned from closed-loop feedback.

A hierarchical framework that couples high-level multimodal reasoning with low-level function-constrained execution for deployable precision medical robotics, and introduces a scalable multi-agent pipeline to generate skill-oriented chain-of-thought data for structured training.

This minimal recurrent behavioral memory is characterized by a compatibility relation: under transitivity its classes attain the exact minimum, while the general case is an entropy minimization over closed compatible state assignments, with exact certificates on finite instances.

PAKT, a framework for kinesthetic teaching in RL, adds a high-performance control stack that maps low-frequency RL actions to high-frequency torque commands and preserves the tracking performance of the impedance controller while improving contact handling and producing smoother policy actions.

This work proposes RoboMP-DINOv2 (Robotics Mask-Prompted DINOv2), a full-scene vision encoder that treats masks as spatial prompts rather than visibility filters, and introduces masked-region color randomization (MCR) to improve appearance robustness, yielding RoboMP-DINOv2-MCR.

An integrated robotics course framework that organizes these activities around a shared robotic artifact, and offers a structured approach for adapting robotics research workflows into interdisciplinary precollege courses.

MachEmbodied-U0, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture, is presented, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture that combines competitive downstream control performance with transferable task-grounding and visual-dynamic capabilities across simulation and the real world.

The results show that the framework enabled all five hands to execute the complete tool manipulation process, achieving dexterous behaviors even from identical, simple reference trajectories, and showcase the framework's adaptability to different hands, tools, and tasks, enabled by its kinematic and geometric foundation.

This work extends planning under a Riemannian metric from unconstrained spaces to constraint submanifolds by applying the induced metric in both a sampling-based planner and a trajectory optimizer.

A ROS-integrated framework, built on Isaac Sim, for large-scale procedural generation of agricultural environments, with built-in support for row crops, orchards, and vineyards and straightforward extensibility to additional crop categories is presented.

DynaForge combines low-frequency global planning with high-frequency object-centric inverse kinematics across task phases, and applies a residual policy to correct actions during dynamic interaction, showing the ability of DynaForge for sim-to-real transfer.

The Cartesian Hand is introduced, a 7-DoF end-effector that rethinks dexterous manipulation by combining independent grasping and relative manipulation within a single end-effector using only linear motion.

The preliminary results of teleoperating Astrobee in a custom zero-gravity MuJoCo-based International Space Station (ISS) simulator through ten repeated trials of transporting a rigid ISS Cargo Transfer Bag (CTB) are presented.

MatcherCompass is presented, a deployment-aware benchmark for choosing local feature matchers in field robotics and provides measured evidence for choosing matching pipelines that fit a robot's sensing conditions and computing hardware.

PhyVisGen, a physically and visually high-fidelity framework for scalable robotic manipulation data generation, introduces an arm-gripper coupling method based on the Incremental Potential Contact (IPC), enabling high-fidelity soft contact throughout complete manipulation trajectories.

A surgical instrument-state logger that clips onto a conventional instrument without modifying the part that enters the patient and fuses a six-axis IMU and a time-of-flight rangefinder with a markerless camera in an error-state Kalman filter under the remote center of motion (RCM) of the trocar is presented.

IndustrialVLA-Bench is presented, an evidence-aware evaluation of six released VLA and WAM systems under a unified reporting schema that evaluates clean capability on LIBERO, non-language robustness on LIBERO-Plus, instruction sensitivity on LIBERO-Para, and observed execution cost.

A deterministic 25 Hz tactile reflex controller is used as a collection-time teacher that shapes grasping behavior in demonstrations for policy learning, while disturbance rejection remains controller-dependent, revealing the boundary of tactile-free policy.

A teacher-student framework combining an improved visual encoder architecture, persistent feature masking, and a novel consensus-gating algorithm to retain useful depth information under unmodeled corruption, which improves robustness where augmentation coverage is missing.

This work adds one feature-alignment term to ordinary VLA training: a frozen world model is run over the training frames once and cached, and the student learns to agree with that cache, indicating a broad representational prior rather than a fragile alignment between two particular networks.

This work proposes CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execution, and introduces the Failure State Recovery Benchmark (FSR-Bench), which evaluates recovery from intermediate failure states under local deviations and structural anomalies.