← Paper Digest

Saturday, November 21, 2026

24 papers added this day. New papers stay for 14 days.

Tactile sensing 4

Grasping 1

Imitation learning and data collection 2

Robot foundation models 4

RL and sim-to-real 2

Legged locomotion 1

Humanoids and mobile manipulation 4

Planning and control 1

HRI and teleoperation 1

Robot hardware and actuators 3

Brain-computer interfaces 1

One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning

Yuxin Jiang, Wenqiang Sun, Jiaqi Li et al.

November 2026

O²LaF learns latent actions from unlabeled video by adapting one pretrained video diffusion transformer into both an inverse dynamics encoder and an action-conditioned video generator. Trained only on egocentric human videos, its latent actions reach an end-effector R² of 0.277 when probed on GR-1 robot demonstrations, versus 0.149 for DreamDojo.

Reference-Free Humanoid Skateboarding via Termination-Shaped Reinforcement Learning

Ganeshvar Soenessardien, Michael Przystupa, Kevin Sebastian Luck

November 2026

A Booster K1 humanoid learns in MuJoCo to push itself along on a four-wheel roller board with PPO and no motion reference, guided only by task rewards and early terminations that rule out exploits. Across three seeds it holds the one-foot-on-board push stance 97.6% of the time and moves the board at 0.27 m/s.

TipDex-VTLA: Learning When to Refine Actions with Touch for Dexterous Manipulation

Xudi Ge, Yepeng Liu, Haifeng Liu et al.

November 2026

A vision-tactile-language-action policy for dexterous hands that estimates how far lighting changes are pushing its actions off course and checks incoming touch against its own tactile forecast to decide how strongly to correct actions not yet executed. On four real tasks it succeeds 73.8% of the time under unseen lighting, against 31.3% for the best baseline.

MoRE: Mixture-of-Experts for Multi-Physics Robotic World Models

Ziyu Zhu, Shaowei Liu, Albert J. Zhai et al.

November 2026

A 3D world model that predicts how object point clouds move under a robot tool and routes each interaction to one of three experts (rigid pushing, deformable pushing, deformable grasping). Without being told the interaction type it matches per-regime expert models, and in simulated MPC it succeeds in 50% of trials against 20% for DINO-WM.

Render the Robot, Generate the World: One Video World Model Across Embodiments

Yash Jangir, Karan Mirakhor, Renos Zabounidis et al.

November 2026

Doppel renders the robot along a planned joint trajectory and conditions a video world model on those renderings plus the actions, so one model covers robot arms, a humanoid and human bodies without embodiment labels. Across three robot-arm datasets it improves PSNR over action-only conditioning by 1.00 dB on held-out trajectories and 1.20 dB out of distribution.

HINT-WAM: Hindsight-Informed Training for World Action Models

Phuong Tuan Dat, Qi Li, Xinchao Wang

November 2026

HINT-WAM post-trains a world action model's action expert by self-distillation, where the same model, also shown the demonstration's future video, supervises the student on the denoising states its own sampler visits. In simulation on LIBERO-90 it raises success from 78.9% (SFT) to 85.2% and forgets less of the original LIBERO suites.

Hierarchical Admittance-Impedance Control for Mobile Manipulator Load Transfer

Minghao Xu, Thushara Sandakalum, Christina Dao Wen Lee, Marcelo H. Ang

November 2026

A Franka arm on a mobile base holds a load while a person steers it by hand. An outer admittance loop turns the person's push into motion, an inner impedance loop supports the load, and the base moves when the arm nears its reach limit. In one 3.3 kg suitcase transfer over 2.44 m, the person applied 7.43 N on average while the robot supported about 35 N.

OmniFish: A Bioinspired, Modular, Reconfigurable Soft Robotic Fish Enabling Multi-Modal Swimming

Mathias Jensen, Saravana Prashanth Murali Babu

November 2026

A 40 cm soft robotic fish whose tendon-driven spine can be locked segment by segment, so a single servo produces all five body-and-tail swimming modes, from eel-like to boxfish-like. In tethered tank tests the stiffest, boxfish-like mode was fastest and most efficient, at 8.14 cm/s with a cost of transport of 2.42.

TapTacTouch: Shape Completion from Sparse Tactile Contacts with Geometric Priors

Yoobin Shin, Jaeyoung Lee, Jieun Kang et al.

November 2026

A robot arm with a 20-DoF hand probes an object with 3x3 pressure pads on its fingers and fits a multi-scale Gaussian process implicit surface to the contacts, with no camera and no training. On six 3D-printed objects, with contacts projected onto the true surface for evaluation, the meshes reach 1.61 mm Chamfer distance and a 95% F-Score.

GALA: Gallery-Level Alignment for Real-Life Vision Decoding from EEG

Philippe Forest, Giulia Lioi, Mai Pham Quyen et al.

November 2026

Calibrate an EEG-to-image decoder to a new user without any labels, by registering the user's growing pool of unlabeled EEG embeddings onto the known gallery of candidate images. On THINGS-EEG-2 with 200 images, top-1 accuracy for an unseen subject rises from 28% to 67% over 53 minutes of use.

Dual-Actuation Emulation of Scaled Relative Orbital Dynamics on a Free-Flyer

Elias Krantz, Pedro Roque, Gunnar Tibert et al.

November 2026

A propeller module on the ATMOS air-bearing free-flyer physically applies scaled orbital (Clohessy-Wiltshire) accelerations, driven by its own MPC, while a separate spacecraft MPC flies the solenoid thrusters. On hardware the spacecraft controller tracks stable relative orbits to within 3 m at orbital scale (3 cm in the lab) and behaves like the same controller in a high-fidelity orbital simulation.

Ego2X: Contact-aware Transfer from Egocentric Human Data to Any Robot

Xinke Lyu, Bowen Yang, Zhicheng Wang

November 2026

Ego2X turns monocular egocentric human video into robot training data by transferring object-frame contacts instead of hand motion, for dexterous hands and parallel grippers. Post-training X-VLA on its converted episodes alone, with no simulator demos, raises success in RoboTwin 2.0 from 40.5% to 67.0%.

ReLoco: Unified Humanoid Locomotion and Fall Recovery via Behavior-Conditioned Motion Priors

Lequn Fu, Yufeng Hu, Yijun Zhong et al.

November 2026

One proprioceptive policy makes a 64.5 kg Tiangong 3.0 humanoid walk, run, get up after falls and resume its command. It is trained with adversarial motion priors conditioned on whether the robot is upright. On hardware it got up after all 34 kick-induced falls in which the policy stayed in control.

LAGR: Language-Aware Grasp Re-Ranking for Task Oriented Grasping

Manav Kulshrestha, Shreyans Jain, Apoorva Vashisth et al.

November 2026

LAGR proposes physically feasible grasps from RGB, depth and segmentation, then re-ranks all of them together against a language task instruction. It is trained on a new set of 2.68 million scored grasps, and on a real Franka it executes a task-appropriate grasp in 93 of 100 trials, against 72 for GATER.

TacPilot: Does Touch Need to Be Everywhere?

Yunzhen Zhang, Yuxiao Zhu, Jie Yang et al.

November 2026

TacPilot adds touch to a frozen vision-only ACT policy. It re-encodes only the fingertip regions whose readings changed, and its corrections to the arm and gripper apply only when separate gates open. In simulated cylinder uprighting it succeeds in 26 of 30 trials, against 21 for an always-on dense tactile residual and 15 for vision alone.

RESCUE Jumper: A Centimeter-Scale Rolling and Jumping Robot for Search and Rescue

Kiran Marques, Shashwat Singh, Ben D'Ambrosia et al.

November 2026

A 125 g, 6.2 cm wide wheeled robot jumps without an extra actuator, driving its wheels in reverse to wind a spring-steel tail that launches it. Changing the winding speed switches jumps from backward to forward, up to 9.2 cm high, and it hopped from gravel onto a 5 cm ledge it could not roll over.

BiCAT: Bimanual Coordination Action Tokenization

Xuanwei Liu, Guipu Cao, Zhongyi Luo, Jiafei Duan

November 2026

BiCAT is an action tokenizer for bimanual VLA policies that gives each arm its own token stream, computed with access to the other arm. It raises mean success on ten RoboTwin 2.0 tasks by 17.6 points over the best of eight tokenizers and succeeds in 113 of 150 real-robot trials, against 74 for OAT.

Magflow: Differentiable Simulation of Industrial-Grade 6D Magnetic Levitation

Philipp Hartmann, Jannick Stranghöner, Klaus Neumann

November 2026

A differentiable, GPU-parallel electromagnetic simulator trains a neural controller for an industrial 6D maglev system, and the controller transfers zero-shot to the hardware at 4 kHz. It turns the mover through full yaw rotations beyond the engineered limit and levitates a plain bar magnet that no hand-built controller supports, at about 0.3 mm RMS position error against under 0.1 mm for the factory controller.

Physics-Informed Tactile-based Shape Estimation of Deformable Linear Objects

Rotem Atari, Stav Ashur, Avishai Sintov

November 2026

Four DIGIT tactile sensors on two grippers, plus the arm's pose, let a ViT reconstruct the full 3D shape of a wire held between them with no camera. On a 550 mm steel wire it reaches 30.5 mm RMSE, against 55.0 mm from gripper pose alone.

Body Schema Policy: Body as the Vision-Action Interface for Efficient Robot Loco-Manipulation

Lechen Zhang, Chenyuan Chen, Muxin Zhou et al.

November 2026

Body Schema Policy is a small diffusion policy that denoises actions on tokens placed along the robot's kinematic tree, each picking out its own image patches. On nine simulated Unitree G1 whole-body tasks it matches the 2.63B-parameter Ψ0 model (221 vs 220 of 270 episodes) with 75x fewer parameters, and succeeds in 16 of 20 trials on a real G1.

Learning Accurate End-Effector Trajectory Tracking with Inertial Feedback for a Quadruped Manipulator

Dohyeon Kim, Seungyong Han, Yeongtae Jung

November 2026

An IMU on the gripper of a Unitree Go2 with a PiPER arm lets a residual RL policy correct arm tracking errors that joint encoders cannot see, such as base motion and backlash. On hardware, motion-capture tracking error averages 16.42 mm, against 20.13 mm for the nominal controller and 18.26 mm for a residual policy without the IMU.

ALERT: Extending Humanoid Motion Trackers with a General and Lightweight Human Avoidance Pipeline

Zhaoyang Li, Chiyu Zhang, Chengxin Xu et al.

November 2026

Adds gated low-rank branches to a frozen, pretrained humanoid motion tracker and trains them with LiDAR-based repulsive potentials, so limbs near people bend away while the rest of the motion stays on track. On a Unitree G1 it completed all 20 trials of each of four dances, kicks and teleoperation runs without collision or fall.

Agile Monoped Hopping on Complex and Discrete Terrain via Kinodynamic Planning with Distilled MPPI Steering

Yue Qin, Denglin Cheng, Jingyu Liu, Yanran Ding

November 2026

FlowRRT plans multi-jump routes for a planar one-legged hopper over gaps, slopes and stepping stones by distilling a multi-start MPPI solver into a flow-matching sampler of all feasible jumps. In simulation it solves 93% of planning problems within 1 s, where SST solves 26% and RL-RRT none.

ThinkWAM: Rethinking Latent Futures for Action Refinement

Haoyun Tang, Baqiao Deng, Enjin Zhou et al.

November 2026

ThinkWAM proposes an action chunk, uses that proposal to correct its predicted future latents, then regenerates the chunk from the corrected futures with the same action head. It reaches 84.76% on LIBERO-Plus without OOD fine-tuning and 64.4% mean success across three out-of-distribution real-robot conditions, against 56.7% for π0.5.

Summaries are written automatically from each paper's text. Figures and videos come from the paper and its project page; all credit goes to the authors.