Paper Digest
Robotics papers worth reading, each with its videos, key figures and a short summary. New papers every day, plus the seminal ones by topic.
♥ Most loved this week
Friday, November 6 18 papers
Tactile sensing 1
Dexterous manipulation 3
Imitation learning and data collection 1
Robot foundation models 2
RL and sim-to-real 3
Humanoids and mobile manipulation 7
3D perception and scene representation 1
Latent RL Priors for Data-Efficient Dexterous Manipulation
November 2026
Distill a large-scale simulated RL policy for a KUKA arm with a dexterous hand into a frozen flow-matching action decoder, then learn only a visual front end from a few demonstrations. In simulation it beats π0.5 and GR00T N1.7 fine-tuned on the full datasets using 10x fewer demos on door lifting and 5x fewer on bimanual assembly.
Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing
November 2026
VLA-Tug is a small LSTM probe on a VLA's backbone embeddings that predicts failures before they happen and names the likely failure mode, with an alarm threshold calibrated to bound both false alarms and missed early detections. On held-out LIBERO-X skills it raises early-detection area by 30% over the strongest learned baseline, at 0.12 ms per step.
Social Humanoid: Socially Responsive Human-Humanoid Interaction
November 2026
A Unitree G1 watches a person through an RGB-D camera and generates a whole-body reaction (handshake, high-five, hug) with a diffusion model over motion tokens shared by humans and the humanoid. On the real robot it succeeds in 90-100% of 30 trials per interaction, with 308 ms median latency.
GPWM: Modeling the World as 3D Particle Motion
November 2026
A generative transformer predicts how the particles and rigid bodies of a 3D scene move, across rigid, deformable, granular and cloth materials, trained on a 25.5M-frame simulated corpus. It cuts prediction error by 31% on average against the best prior learned simulator, and planning in its latent noise reaches 0.48-0.57 task progress on pushing where action-space search stays at or below 0.01.
Terrain-Indexed Motion Priors and Geometric Support for Extreme Humanoid Parkour
November 2026
One depth-based humanoid policy learns to climb and cross obstacles up to about 1 m tall from human motion clips, then is retrained to place its hands and knees where they suit the robot. Deployed zero-shot on a Noetix E1, it clears 29 of 30 single obstacles and 4 of 5 three-obstacle courses.
HITCH: Teaching a Vision-Language Model to Operate a Humanoid through a Whole-Body Harness
November 2026
A harness lets a VLM measure 3D points from depth and command a Unitree G1's pelvis, torso, hands, walking and gaze, and Qwen3.8-27B is fine-tuned on teacher trajectories from five base tasks. It solves 51% of unseen SIMPLE episodes (95% with five trajectories per task) and carries a box on a real G1 in 13 of 20 tries with no real training data.
Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation
November 2026
S2C uses a vision-language model to bring the robot near the contact point, then learns the final force-aware insertion with human-in-the-loop residual RL on the real robot, trained on wrist images with randomized backgrounds. Under new tablecloths and lighting it averages 69-84% success on six tasks, while HIL-SERL and HIL-ConRFT mostly fail.
Playing Soccer Like Humans Do: Learning Versatile and Agile Humanoid Soccer via Latent Motion Priors
November 2026
SoccerBot trains one skill-conditioned RL policy that moves, dribbles, traps and kicks a ball on a Unitree G1, acting as a residual on a latent motion prior distilled from human soccer motion capture. In simulation it kicks successfully 97.0% of the time and dribbles 89.9%, and it transfers zero-shot to the real robot with motion-capture ball tracking.
GRASP: Gradient-Guided Sampling for Contact-Rich Physics-Based Motion Retargeting
November 2026
GRASP turns kinematically retargeted human motions into physically executable robot motions by sampling in simulation and steering the search with gradients fitted to past rollouts, with no differentiable simulator. It succeeds on 92.8% of 1352 bimanual OakInk2 demonstrations (best baseline 81.0%), and its refined references improve PPO tracking on dexterous hands and a Unitree G1.
PACT: Pose-Robust Actuation Co-Design for Tendon-Driven Robotic Hands
November 2026
PACT jointly picks tendon routing, moment arms and capstan sizes for a tendon-driven finger, so that one design covers the required fingertip forces even at its weakest pose while keeping 5 Hz joint bandwidth. For a human-sized four-DoF finger, it raises worst-pose task-force coverage from 0.24 to 0.88 over a hand-designed baseline. On the built prototype, measured force falls about 24.5% short of prediction because of tendon friction.
GSBR: Geometric Support Behavior Regularization for Online RL
November 2026
GSBR fine-tunes a frozen imitation-learned base policy with online RL, penalizing actions only by how far they fall outside the base policy's estimated support. Across 19 simulated tasks on four benchmarks it raises average success from 33% for the base policy to 95%, with about 23% higher normalized throughput than the next-best RL method.
HLO-AMP: Hierarchical Loco-Manipulation from Object-Aware Motion Priors
November 2026
A Unitree G1 learns bimanual box pick-and-place from a low-level controller trained to imitate human motion capture with the box in the simulation, steered by a high-level RL policy. One deployed policy carries boxes up to 7 kg and recovers from drops. In simulation it succeeds 80.7% of the time, vs 50.3% for a whole-body controller trained without the object.
Physical Diffusion Policy via MPM-Guided 3D Gaussian Simulation
November 2026
Estimate each object's stiffness, plasticity and viscosity by fitting a Gaussian-splat physics simulation to a demonstration video, then condition a mixture-of-experts diffusion policy on those parameters. On a real robot, pick-and-place success across 18 everyday objects rises from 28.9% (Diffusion Policy) to 62.5%.
RAFT: Reasoning-Aligned Fine-Tuning Improves Robustness of VLA Post-Training
November 2026
Before fine-tuning a VLA on a few demonstrations, RAFT trains LoRA adapters to predict VLM-generated reasoning annotations (boxes, keypoints, gripper traces), then freezes them. On a real DROID arm it succeeds in 75% of out-of-distribution trials versus 28% for plain fine-tuning, and on a bimanual YAM task it reaches 70% versus 36% for the best baseline.
KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL
November 2026
An open-source desktop robot (under $2500) that plays the two-player game KLASK with two CoreXY gantries, plus an Isaac Lab digital twin for adversarial multi-agent RL. A self-play PPO policy trained with a learned actuator model transfers zero-shot to the hardware, but wins only 1 of 10 games against a recreational human.
ReContact: Reconstruct and Retarget Human Contacts from Video for Contact-Rich Humanoid Manipulation
November 2026
ReContact turns a human video into an object-centric contact plan (which body part touches which point of the object, pressing in which direction) and trains a humanoid policy rewarded for following it. In simulation it completes a thigh-supported box regrasp into a two-palm bottom hold in 83.5% of episodes versus at most 0.16% for adapted baselines, and it runs nine tasks on a real Unitree G1.
Visuo-tactile Diffusion Policy for Robotic Manipulation with Auxiliary Tactile Dynamics Prediction
November 2026
A visuotactile diffusion policy for simulated UR5 assembly, with a training-only head that predicts how the fingertip images change two steps ahead. The full model reaches 59.0% success against 42.7% for vision only, while adding touch without the auxiliary loss drops to 33.7%.
MAPO: Mixture of Experts with Alternating Policy Optimization for Universal Humanoid Motion Tracking
November 2026
MAPO trains a mixture-of-experts humanoid motion tracker by clipping the router and expert updates separately, since PPO's single KL measure misjudges how much each part changed. It reaches 86.6% tracking success versus 83.4% for PPO with the same MoE, and consistently tracks 182 motions where PPO with MoE fails (the reverse happens for 1).
Thursday, November 5 30 papers
Tactile sensing 6
Dexterous manipulation 1
Imitation learning and data collection 6
Robot foundation models 4
RL and sim-to-real 1
Humanoids and mobile manipulation 7
Computer vision for robots 1
3D perception and scene representation 1
Planning and control 2
HRI and teleoperation 1
OopsieRecover: Learning Transferable VLA Corrections from Semantic Interventions
November 2026
OopsieRecover turns a handful of human interventions, each with a short note on why, into gated costs over 3D point sets that decide when and how to steer a frozen pi0.5 VLA. On a real DROID setup it raises task progress from 35.1% for the next-best method to 61.0%, and the corrections carry over to new object poses and scenes.
MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation
November 2026
MoMaSplat rebuilds the scene and the manipulated object as separate Gaussian splats from a mobile robot's own data, then re-renders whole demonstrations, including the object moving, from new base poses. On five real TIAGo tasks it succeeds on 37% of rollouts from unseen base poses, against 17% for the best baseline.
TactileLab: Sim-to-Real Dexterous Robot Manipulation with Efficient Shear-Sensitive Tactile Simulation
November 2026
TactileLab adds simulated tactile flow, a dense shear field computed from rigid-body contact motion in IsaacLab, so RL policies can feel tangential contact at scale. Trained only in simulation, a LEAP Hand policy using contact depth plus flow makes 1.95 real in-hand rotations in 30 s, against 0.82 with proprioception alone.
Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation
November 2026
Spatial-UMI-Dream pretrains a 5B world action model on 605 hours of UMI handheld-gripper data to predict future RGB, stereo-derived metric depth and actions together. It reaches 85.0% average success on six real bimanual tasks, 24.2 points above the best baseline (π0.5).
cuRoboV2-Fast: Fast Torque-Limited Collision-Free Motion Planning
November 2026
A GPU motion planner that optimizes B-spline trajectories with the payload in the dynamics, then retimes them under velocity, acceleration, jerk and torque limits. It plans a 3 kg-payload motion in 4.4 ms on an RTX 5090, 14.7x faster than cuRoboV2, and cuts real pick-and-drop cycle time by 34.6%.
Perceptive Humanoid Motion from Simulation
November 2026
HALO trains a Unitree G1 humanoid only on synthetic vision-language-motion data rendered in 1,000 procedurally generated rooms. Zero-shot, it sits, crouches, crawls, sidesteps through doors and pushes boxes in six unseen real homes, succeeding in 91% of 360 trials.
Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement
November 2026
They post-train the pi0.5 VLA online with RL on up to 144 simulated pick tasks at once and test on held-out scenes and objects. With critic-based recipes the gains grow with the number of training tasks, up to +58 points on unseen scenes and +39 on unseen objects, while filtered fine-tuning generalizes much less.
Which Physical Tactile Cues Matter for Contact-Rich Imitation Learning? A Controlled Real-Robot Study
November 2026
From one GelSight-style sensor stream they derive tactile RGB, normal/depth maps and marker flow, and compare them as Diffusion Policy inputs over 720 real-robot trials. Touch raises success from 57.8% to 78.9%, and marker flow is the best single cue at 74.4%.
TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics
November 2026
TwinBridge builds Gaussian-splatting digital twins of lab benches, pretrains a policy in them, and distills simulator-derived progress labels into a visual reward model for human-in-the-loop RL on the real robot. Across five lab tasks it reaches 98% mean autonomous success with at most 25 minutes of real-world interaction per task.
Online Adaptation to Latent Physical Properties for Learning from Demonstration
November 2026
A Diffusion Policy is conditioned on a latent physical-property estimate that is updated online from a learned dynamics model's prediction errors. This lets the robot regrasp or re-push objects that look identical but have different centers of mass. On a real xArm7 it raises pouch-placement success from 40.7% to 66.7% over a standard Diffusion Policy.
LumiTac: Compact, High-Rate Six-Axis Optical Tactile Sensing for Human-Robot Interaction
November 2026
A camera-free optical tactile sensor, 12 mm across and under 2 g, that reads three forces and three moments from 20 colour light channels for about USD 7. A small MLP reaches R² of 0.966-0.994 per axis at about 300 Hz, and the sensor guides a real gripper through admittance control.
Correct Robots Before They Make Mistakes: Proactive Human-in-the-Loop Intervention via Preference Learning
November 2026
An XR headset shows the operator the policy's predicted gripper path so they can take over before a mistake, and each rejected prediction is paired with the correction that followed for preference post-training. With five correction episodes, mean real-robot success over HG-DAgger rises from 44.0% to 70.3% for a diffusion policy and from 57.8% to 76.9% for X-VLA.
ELA: End-to-End Latent Action Policy Learning from Video Demonstrations
November 2026
ELA trains a latent action model, a latent-action policy and a small action decoder together, so an imitation policy can learn from human or unlabeled robot video plus a few action-labeled demos. With 10 robot demos and 40 human videos per task, it raises real-robot success from 48% (Diffusion Policy) to 70%.
Ctrl-F: Force as an Interface for Humanoid Loco-Manipulation
November 2026
Ctrl-F gives a humanoid motion tracker a 3-D force command for each hand or foot, trained without objects, plus a planner that sets those forces from the object's state. In simulation it keeps hand-task completion above 90% at 1.5x nominal object mass, where force-blind trackers drop to zero, and a real Unitree G1 pushes and kicks 20 kg boxes.
GUILD: Guided Iterative Data Collection for Imitation Learning
November 2026
GUILD tells teleoperators which tasks to collect next. A VLM proposes candidate tasks in accessible environments, and data attribution scores how much each task's demos help a hard-to-reach deployment task. In open-ended real-world collection it beats uniform collection over the same VLM proposals by about 25% average success, and beats two expert roboticists on average.
RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On
November 2026
RoboTryOn turns egocentric human videos into robot demonstrations by generating a video of the robot making the same motion and reading its actions back with an inverse dynamics model. On two bimanual robots with dexterous hands, it lifts success on seven tasks that have no robot demonstrations from 2% to 60% on average.
Asynchronous Robot Policies
November 2026
ARP splits a vision-language-action policy into two processes. A slow VLM keeps refreshing a compact memory, while a small vision-action expert reads it and acts at a much higher rate, trained to cope with stale memory. On LIBERO it keeps 81.8% success with the VLM updating at only 0.5 Hz, and when the target shifts 5 cm mid-reach it succeeds 51.5% of the time against 9.5% for a π0-style baseline.
DexHOT: Learning Hand-Object Configuration Transfer for Dexterous Manipulation
November 2026
One RL policy for a 22-DoF hand learns to move between grasps that fix both the finger joints and the object's pose in the hand, then chains these short moves into longer tasks. It succeeds on 61.5% of 200 real-robot transfers and 27 of 30 demonstration-guided task trials.
Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight
November 2026
A humanoid policy samples several whole-body and hand command sequences, predicts in latent space where each would lead, and executes the one that makes the most visual progress and is most temporally consistent. On a Unitree G1 it succeeds 85.7% on seven tasks (65.7% with unseen objects) versus 70.0% (48.6%) for GR00T N1.7.
ReflexArc: Bottom-Up Integration of Instantaneous Tactile Reflexes into Whole-Body Humanoid Control
November 2026
A full-body tactile suit on a Unitree G1 triggers whole-body withdrawal reflexes that reach the motors within 10 ms, and the learned whole-body policy is trained to keep balance without cancelling them. Compared with the same reflex delayed by 20 ms, the first force peak drops by 34.1% and the contact impulse by 2.15x.
MABEL: An Open Anthropomorphic Mobile Bimanual Platform for Teleoperation and Learning
November 2026
An open-source 56-DOF mobile bimanual robot with dexterous hands, a pitching torso, a lift and an active neck, for a US$8.1k parts cost. Apple Vision Pro head and hand tracking drives the whole body with 137 ms video latency, and an ACT policy trained through the same controller succeeds in 8 of 10 grasp-and-place trials.
FEIJOA: Task-Driven Grounding and Execution for Mobile Manipulation
November 2026
A language-model agent for mobile manipulation that grounds each instruction against a raw RGB-D scan when it arrives, and checks every skill's feasibility before running it and its effect afterwards. It resolves 94.2% of 103 open-ended grounding queries exactly (68.0% for the best prebuilt map) and completes 35 of 50 real tasks on Spot.
Robot-Matched Soft Fingers for UMI Data Collection: Lessons from 100 Hours of Pick and Place
November 2026
A battery-powered handheld UMI with soft, angled fingers that match the robot's gripper, used to collect 99.7 hours of pick and place over 53 objects. Mid-training π0.5 on this data raises success after fine-tuning on unseen objects from 35% to 57% on a Galaxea R1 Pro.
Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation
November 2026
Pixel is a wheeled humanoid that costs under $15,000. The robot, its teleoperation interfaces, a wearable human-demonstration rig, the whole-body controller and the policy were designed together, so human and robot data share one action space. Policies trained only on wearable-rig demonstrations reach 82.0% average task progress on three household tasks, and collecting those demonstrations is 4.2-6.2x faster than teleoperation.
Pixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human Demonstrations
November 2026
Pixel-UMI turns head-and-gripper human demonstrations into whole-body robot training data by retargeting them against a 3D reconstruction of each scene, so the policy learns postures that clear obstacles. Across five real mobile-manipulation tasks it reaches 87.0% average task progress, and scene-aware retargeting alone adds 64 points.
TAMPAgent: Agentic Belief-Space Planning for Mobile Manipulation
November 2026
A language-model agent writes belief-space task-and-motion plans, and perception, grasp and motion tools must certify each action's constraints before the robot moves. On simulated kitchen tasks with an RB-Y1 mobile manipulator it reaches 77.2% success, against 57.2% for Code as Policies and 61.1% for Graph as Policy.
Exploring Proximity and Tactile Sensing for Robotic Manipulation
November 2026
ToFTouch puts three 4x4 multizone time-of-flight depth sensors next to an optical pressure patch on one gripper finger, so the robot can sense objects before and during contact. Closing the gripper early on ToF readings cut grasp cycle time by 7.4%, and ToF depth correction picked items 9/10 times at 2 cm depth errors where picking at the nominal depth failed every time.
ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation
November 2026
ForceLDM distills future force/torque and optical-flow features from a privileged teacher into a π0-based student policy that sees only current observations. On five real-robot contact-rich tasks it averages 87.1% success, 14.9 points above the strongest baseline.
AnchorHEC: Targetless Hand-Eye Calibration of Wrist and Fixed Cameras
November 2026
AnchorHEC calibrates a robot's wrist camera and fixed cameras in one run from ordinary RGB images of the scene and the arm's forward kinematics, with no calibration board. On a physical xArm6 with 15 wrist poses it reaches 1.2-1.4 cm wrist-camera and 1.6-1.8 cm fixed-camera translation error, versus 2.4-10.2 cm and 3.4-8.8 cm for the JCR baseline.
HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation
November 2026
A fine-tuned VLM keeps a running text memory of task events, such as which buttons were already pressed, and feeds commands to a π0 low-level policy, so the robot can count, follow orders and recall information across instructions. On 10 real-robot memory tasks it reaches 85.7% subtask success within episodes (vs 72.9% for the best baseline) and 89.2% across episodes.
Wednesday, November 4 4 papers
Tactile sensing 1
Dexterous manipulation 1
Imitation learning and data collection 2
AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
November 2026
Pretrain a π0.5-based policy on 16,151 hours of handheld-gripper demonstrations with no robot data at all, then post-train it per task on a few hours of handheld data. On ten long bimanual tasks at a site outside its data, A-0 averages 78% success against 27% for the best of four post-trained VLA baselines.
PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation
November 2026
A sub-$50 gripper fingertip that fuses a dense piezoresistive array with magnets and magnetometers into a 12x32 map of normal and shear force. With it, visuo-tactile diffusion policies reach 91.7% success on test-tube prep, grain scooping and salt pouring, against 45% for vision alone.
DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection
October 2026
A hand-held rig that carries the robot's own 20-DoF hand and camera, so demonstrations need no retargeting. Simple joystick skills drive the fingers, and the commanded joint targets, not measured states, are logged as actions; that alone lifts policy success from 11% to 64%.
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
June 2026
Pretrain one dexterous-hand RL policy by playing with a thousand random objects in simulation, then finetune it on sparse-reward assembly. Play2Perfect learns 33x faster than RL from scratch and transfers zero-shot to 0.5 mm insertions on a real robot.
New papers stay for 14 days; seminal ones stay for good.
A reading list of foundational papers by topic, oldest first. ★ marks the must reads, the few to start with.
Robotics foundations 51
Tactile sensing 40
Dexterous manipulation 31
Grasping 36
Imitation learning and data collection 43
Robot foundation models 36
RL and sim-to-real 69
Legged locomotion 35
Humanoids and mobile manipulation 28
Computer vision for robots 36
3D perception and scene representation 56
Planning and control 63
HRI and teleoperation 43
Human motion prediction 20
Assistive robotics and haptics 20
New to a topic? Each page starts with its seminal papers, then the newest work.
Robotics foundations
The classic papers the field is built on, from kinematics, control and estimation to planning and grasp analysis.
51 papers · 51 seminalTactile sensing
Sensors that let robots feel contact, and policies that use touch.
48 papers · 40 seminalDexterous manipulation
Multi-fingered hands for grasping, in-hand reorientation and assembly.
38 papers · 31 seminalGrasping
Choosing and executing grasps, from analytic grasp quality to grasping learned at scale.
36 papers · 36 seminalImitation learning and data collection
Learning from demonstrations, from teleoperation and handheld rigs to human video.
63 papers · 43 seminalRobot foundation models
Large pretrained vision-language-action policies and the data behind them.
48 papers · 36 seminalRL and sim-to-real
Reinforcement learning in simulation and transfer to real robots.
81 papers · 69 seminalLegged locomotion
Quadrupeds and bipeds that walk, run and climb, mostly with controllers learned in simulation.
36 papers · 35 seminalHumanoids and mobile manipulation
Humanoid whole-body control and teleoperation, and mobile robots that manipulate.
45 papers · 28 seminalComputer vision for robots
Features, geometry and calibration, then detection, segmentation, depth and tracking, the vision that robot perception builds on.
38 papers · 36 seminal3D perception and scene representation
Object pose tracking, Gaussian splatting and building simulations from the real world.
60 papers · 56 seminalPlanning and control
Motion planning, trajectory optimization, model-predictive control and task-and-motion planning.
67 papers · 63 seminalHRI and teleoperation
Human-robot interaction, shared autonomy and the teleoperation systems used to collect data.
47 papers · 43 seminalHuman motion prediction
Predicting how and where people will move, from trajectories and gait to intent, for robots that work around people.
20 papers · 20 seminalAssistive robotics and haptics
Assistive arms, prostheses, rehabilitation robots and the haptic feedback that connects them to people.
20 papers · 20 seminalSummaries 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.