Sunday, November 8, 2026
10 papers added this day. New papers stay for 14 days.
Tactile sensing 1
Imitation learning and data collection 2
Robot foundation models 2
RL and sim-to-real 1
3D perception and scene representation 1
Planning and control 3
A Unified Fractal Impedance Control Framework
November 2026
Packages Fractal Impedance Control into one open-source library and GUI that run the same controllers in MuJoCo and on real arms, and ports the H-PMP architecture, which nests task-space and joint-space admittance control, to a Kinova Gen3. H-PMP tracks a figure-eight with 7.8 mm RMSE against 12.6-43.2 mm for earlier FIC controllers, and overshoots least (23.4 mm) when a wall it presses on suddenly drops away.
VREgo: Consumer VR Headsets for Learning Robot Manipulation from Egocentric Demonstrations
November 2026
Records manipulation demonstrations on a consumer VR headset (PICO 4 Ultra), using its own hand tracking and stereo cameras, and trains HumanEgo-style policies from them. In simulation, 40 demonstrations place a cube in 60-74 of 100 unseen layouts, close to Project Aria data, and a two-move stacking task rises from 2% to 93.8% after trajectory rewrites and execution rules.
An Empirical Study of Reinforcement Learning for Keypoint Positioning of Deformable Linear Objects
November 2026
PPO policies trained in GPU-parallel MuJoCo Playground move a rope held by a Franka arm so that its tip, or its tip and then its grasped end, reaches targets on a table. Trained with noise and domain randomization and fed markerless RGB-D keypoints, they transfer zero-shot and succeed in 9/10 single-point, 10/10 disturbance-recovery and 8/10 two-point real trials.
Adaptive Hybrid Force-Vision Control with EMG-Derived References for Deformable Bottle Manipulation
November 2026
A TIAGo Pro gripper squeezes lab wash bottles by tracking grip-force profiles recorded from a person's forearm EMG, combining fingertip force feedback with camera-estimated bottle deformation. Across 12 bottle, volume and squeeze-count conditions it dispenses within 6.54 mL of the human demonstrations on average, against 15.92 mL for force control alone.
Dynamic Shape Control of Soft Trunk Robots
November 2026
The authors learn a 6-dimensional nonlinear reduced model of a tendon-driven soft trunk from 5 h of hardware data and use it in MPC to control the shape of the whole body. On hardware it holds target shapes to 5.1 mm mean error, about 11x lower than the best linear model, and balances a tennis ball on the tip for over 25 s.
Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action
November 2026
Instead of showing an LLM agent camera images at every step, they give it the scene's 3D geometry as text (object faces, edges and goal residuals) grounded locally from RGB-D. On simulated SO-100 tasks this raises online tower-relocation completion from 30% to 84% while using about half the tokens.
HiLo-WAM: Decoupling Long-Horizon Task Evolution and Local Dynamics in World Action Models
November 2026
HiLo-WAM splits a world action model's video prediction into a sparse long-horizon stream that tracks task progress and a dense short-horizon stream for robot-object contact, both guiding one action generator. It reaches 93.70% on RoboTwin 2.0 and completes 33% of long block-assembly trials on a Fourier GR-3, against 23% for π0.5.
Spectrally Routed Diffusion Policy for Multi-Task Robotic Manipulation
November 2026
SR-DP trains one diffusion policy on several tasks, then adapts it per task by re-weighting the SVD components of its denoiser layers. It averages 68.4% on six RoboTwin tasks, beating per-task specialists by 3.8 points, and raises real bimanual success from 24.0% to 43.0%.
VerifLM: Physically Verified Image-Edit-Guided Goal Pose Generation for Robotic Manipulation
November 2026
VerifLM edits a scene image to show the goal, recovers a 6-DoF object pose from the edit, then searches around it and checks candidates in MuJoCo digital twins. On nine real KUKA tasks it reaches 74.1% task-planning success, against 47.2% for the best baseline (Goal-VLA).
W2A: Distilling World Priors into Action Models for Real-Time Robotic Control
November 2026
W2A distills a video diffusion model's intermediate features into a small action policy during training, then drops the video model at deployment. It reaches 95.9% on LIBERO at 55 ms per prediction, about 21x faster than mimic-video, and 65.3% success across 15 real Franka tasks versus 34.2% for OpenVLA.
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.