Monday, November 16, 2026
20 papers added this day. New papers stay for 14 days.
Tactile sensing 1
Imitation learning and data collection 3
Robot foundation models 2
Legged locomotion 2
Humanoids and mobile manipulation 2
Planning and control 6
HRI and teleoperation 3
Brain-computer interfaces 1
Training Reasoning Models in Simulation to Natively Use Real Robots
November 2026
An open-weight 27B reasoning model learns to drive robot arms the way computer-use agents drive a PC (look at camera images, reason, output the next end-effector pose), trained with RL only in simulation and without demonstrations. On a real dual-arm robot it never saw in training it succeeds in 18 of 30 trials; the base model succeeds in none.
FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices
November 2026
FETTUCCINE swaps the audio front end of off-the-shelf speech-recognition models (Whisper, Parakeet) for a neural adapter and decodes intracortical speech-motor activity straight to text, with no n-gram or LLM stack. It reaches 4.39% word error rate on the Brain-to-Text 2025 benchmark and runs on an iPhone 15 Pro Max at up to 370x real time.
Modeling the Frictional Contact of Continuum Robots with Environments through Linear Complementarity Problem
November 2026
A quasi-static model of continuum robots rubbing against their surroundings solves contact forces, sliding and robot shape together as a linear complementarity problem, so it captures sticking, sliding and hysteresis. On a 287.9 mm tendon-driven robot pressed against a wall, the maximum tip error drops from 45.4 mm (frictionless model) to 5.85 mm.
Disturbance-Aware Informative Planning in Spatiotemporal Environments
November 2026
A two-stage planner for persistent monitoring first measures unknown wind only along the routes that matter for monitoring, then optimizes trajectories under the learned wind. In four simulated scenarios it spends 25.0-52.3% less time learning the wind than mapping it across the whole workspace.
Toward Resilient Self-Driving Laboratories through Telerobotic Interventions
November 2026
A SpaceMouse interface lets a person take over a UR3e arm when a self-driving lab's automation fails. With six novice operators on three fault-recovery tasks, controlling pitch and yaw with separate keys raised success from 70.5% to 80.4% and cut task time by 25.6 s.
When Will You Hand It Over? A Hidden Start Delay Makes Self-Play Handover Robust to Unfamiliar Partners
November 2026
A simulated Unitree G1 that learns to receive a parcel by PPO self-play succeeds in 90-95% of handovers with its own partner but only 31% with partners it has never met, because it learns when its partner starts. Adding a random hidden start delay to the partner raises success with unseen partners to 80% in both training seeds.
PROOF: Perceptive Robustness via Out-of-Distribution Fallback for Legged Locomotion
November 2026
A depth-camera parkour policy for the Unitree Go2 that estimates how uncertain its terrain features are and switches to proprioception-only walking when vision is corrupted. Under strong simulated depth corruption it keeps 95-100% traversal success where a student without a learned fallback drops to 0%.
Objectives as Policies: Vision-Language Model Cost Programs for Contact-Rich Manipulation
November 2026
A VLM writes a multi-stage cost program for a sampling-based MPC from a fixed library of cost terms, refines it on rollouts in a real-to-sim digital twin, and the same program then runs on the real arm. Across four contact-rich tabletop tasks with moved objects, programs that succeed in simulation succeed in 32 of 40 real executions.
PoliMop: Policy-in-the-Loop Motion Planning in 3D Spaces for Mobile Robots
November 2026
A kinodynamic RRT planner that grows its tree with simulated rollouts of the robot's own locomotion policy, so one planner finds routes for a quadruped, a humanoid and a wheeled robot through multi-level 3D scenes. Guiding samples along a mass-point path cuts mean planning time by about 63%, and it solves all 830 benchmark planning problems in simulation.
Reusing Locomotion Training Recipes Across Humanoids via Body-Aligned Virtual Joints
November 2026
A kinematic layer lets humanoid locomotion policies act in a shared body-aligned joint space, so one unmodified RL recipe trains well on three humanoids with different leg-axis layouts. On a Unitree G1 it cut heading drift from 5.31 to 0.89 deg/s of yaw rate.
Multimodal Person Concept Model for Person Identification under Varying Observation Conditions
November 2026
A nonparametric Bayesian model groups a few 10 s clips of visual, voice and transcript features into one concept per person, without labels or the number of people, and later identifies people from those concepts. Over eight conditions with six participants it averages 0.89 accuracy, matching k-means given the true head count (0.88), and a Toyota HSR uses it to recall what a person said before.
ERA: Error-Resistant Autonomous Object Navigation with Predicted Depth
November 2026
ERA finds named objects in unseen buildings using depth predicted from RGB instead of a depth sensor. It lets later views erase false obstacles from the map and keeps exploring reachable free space when no frontier is left, reaching 70.1% success on HM3D v2 (MVP-Nav 59.4%) and 11 of 12 runs on a real wheeled humanoid.
On the Utility of Pre-Trained Visual Representations for Policy Learning of Contact-Rich Insertion Tasks
November 2026
A controlled study of which visual features help diffusion policies with tight insertion, comparing DINOv2, Theia, segmentation masks and a new contact-centric map in simulation and on a real book-insertion task. The best feature changes even between near-identical tasks, and only ground-truth contact information helped in every simulated setting.
TouchTwin: Scaling Human Touch Data via Real-to-Sim-to-Real
November 2026
Rebuild glove-recorded human manipulation in MuJoCo and let the measured touch set each finger's contact and closing force. A hand policy trained on these replays grips at 0.99x the recorded force, against 0.31x for pose imitation and 1.55x for vision-based replays.
X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot
November 2026
AgiBot's X-Nav takes a Lingxi X2 humanoid on a language-instructed 96.6 m walk from an office lobby to a store in the next building, with no map and only the built-in RGB camera driving its vision-language navigation model. Adapting the model in a Gaussian-splat twin of a site raises closed-loop success within 3 m from 40% to 80%.
Grounding Object-to-Object Hazard Reasoning into 3D Risk Fields for Task-Conditioned Safety
November 2026
From one RGB-D image and the task, a VLM decides whether to refuse the task or which object pairs to keep apart, and the hazards become 3D risk fields that steer a Franka's motion. In simulation it reaches 81.4% safe success against at most 51.7% for baselines, without ever refusing a safe task.
Racing the Clock: Teaching VLNs Budget-Conditioned Object Search
November 2026
The authors fine-tune the Uni-NaVid navigation model to find as many target objects as it can within a step budget stated in the instruction. It learns from a room-level planner that cannot see inside unexplored rooms. On held-out HM3D scenes it finds 72.7% of reachable targets at 2000 steps, versus 65.5% when trained on a planner that knows every target location and 44.8% for the pretrained model.
Runtime Safety and Emergency Stops on a Full-Size Humanoid: Deployment Lessons and a Case for Graduated Force Authority
November 2026
A runtime safety layer and hard-wired e-stop for an open-source Unitree H1-2 humanoid stack, tested by pushing the standing robot until it lost balance. Under sampling-based MPC the operator had to press the e-stop in every trial, which drops the 70 kg robot, while a learned policy recovered in 14 of 15.
Bind-WAM: Binding-Uncertainty-Guided Selective Future Imagination in World Action Models
November 2026
Bind-WAM lets a world action model imagine future video only when the objects named in the instruction are hard to pin down in the current image, and otherwise predicts actions directly. On a real bimanual robot it averages 66.6% success against 57.6% for always imagining, while imagining at 28.4% of replanning steps.
Camera equalisation of an 11.5x drop in environmental illuminance: four imitation-learning policies on an SO-101 arm
November 2026
Four imitation-learning policies (ACT, SmolVLA, Diffusion Policy, pi0.5) on an SO-101 arm were run at about 520 and 45 lux, and success went from 20/40 to 19/40. Automatic exposure left the front camera's images only 3% darker, so lux alone does not describe what a policy sees.
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.
