archive
Every paper Pith has read. Search by title, abstract, or pith.
2900 papers in cs.RO · page 2
-
DEVO exports sparse point clouds matching EMVS at 5 cm
Extending Deep Event Visual Odometry with Sparse Point-Cloud Export
-
Teleoperated robots steer catheters 7000 km away
Remote Teleoperation of Endovascular Intervention Robots: A Systematic Review
-
Memory lets robots act on objects they can't see
Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
-
4D trajectories and sparse tracking enable zero-shot robot-object tasks
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
-
Sparse keypoints in behavior model enable zero-shot humanoid interactions
Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors
-
Evidence hierarchy lifts Bayesian threat classification to 95%
An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion
-
Spike timing distinguishes objects whose features are merely rearranged
Temporal Coding as a Substrate for Sensorimotor Object Inference: A Spiking Reinterpretation of Thousand Brains Architecture
-
Unified risk map improves safety margins in occluded driving
Learning A Unified Risk Map for Autonomous Driving in Partially Observable Environments
-
Visual primitives raise robot pick-and-place success by 27%
Action with Visual Primitives
-
Pairwise metric on logged pairs lifts latent planning success to 97 percent
Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics
-
30B agents rival 1T models with 25-95% fewer tokens
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
-
Rewards from five demos generalize across robot visual changes
Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations
-
Transformer infers contact states to adapt robots on hardware
CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation
-
Robot lifts unknown boxes stably by estimating mass on the fly
Industrial Dual-Arm Box Handling via Online Inertial Estimation and Convex Wrench Optimization
-
Dataset records real flooded roads for self-driving cars
FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments
-
Tactile sensor gains vary by task and material
TacO: Benchmarking Tactile Sensors for Object Manipulation
-
Grid map cuts robot swarm foraging time by 33%
A Visitation Grid for Complete Coverage Foraging in Robot Swarms
-
Humanoid navigation success rises from 12% to 94% with adaptive memory
Learning to Evolve: Multi-modal Interactive Fields for Robust Humanoid Navigation in Dynamic Environments
-
Neural bids raise quality in decentralized robot task allocation
Auction-Consensus Algorithm with Learned Bidding Scheme for Multi-Robot Systems
-
Low-cost UAV detects structural damage via video frequency shifts
Non-Contact Vibration-Based Damage Detection of Civil Structures Using a Cost-Effective Autonomous UAV
-
Higher-order beliefs speed robot teams without messages
Higher Order Reasoning for Collaborative Communicationless Mobile Robot Operations
-
Fused detectors enable accurate proprioceptive odometry for legged robots
OCELOT: Odometry and Contact Estimation for Legged Robots
-
Action-updated scene prior lifts robot task success
EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
-
Soft sleeve actuator force drops from 112 N to zero over 40 mm extension
Analytical and Experimental Force Analysis of a Soft Linear Pneumatic Actuator
-
SafePBDS turns task safety into certifiable robot accelerations
Safe and Steerable Geometric Motion Policies for Robotic Dexterous Manipulation
-
One platform unifies the full world model research pipeline
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
-
Scene graph matching grounds 3D objects from language without training
SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
-
4D geometry supervision lifts robot video models to 81% success
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
-
VLMs give better 3D vehicle dimensions than lidar in occluded cases
Improving 3D Labeling in Self-Driving by Inferring Vehicle Information using Vision Language Models
-
GNN approximates altruistic robot transfers for scaling teams
Learning Altruistic Collaboration in Heterogeneous Multi-Team Systems
-
Teams adapt ergodic coverage online for unknown environments
Mind the Gaps: Multi-Robot Feedback-Driven Ergodic Coverage in Unknown Environments
-
Vision-IMU attention fusion cuts hand tracking error by 16%
AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking
-
Physics-grounded sampling and zero-shot curation expand a single demonstration into a…
PGDG: Physically Grounded Data Generation for Robust Bimanual Policy Learning from a Single Demonstration
-
Wider contact force ranges boost microgravity robot stability
Motion Design for Grasp-Based Dynamic Locomotion in Microgravity
-
Simulation-trained RL policy shapes real microfibers at 40 Hz
Closed-Loop Sim-to-Real Reinforcement Learning for Deformable Microfiber Shape Control
-
Swarm robots cover assets with redundancy using local rules
Distributed Multi-Coverage for Robot Swarms
-
VR shared control guides drone teams through unknown spaces
Flying Together: Human-Guided Immersive Shared Control for Aerial Robot Teams in Unknown Environments
-
Unified model generates simulation-ready 3D assets across object types
PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects
-
Diffusion assistance cuts teleop task times 40%
HITL-D: Human In The Loop Diffusion Assisted Shared Control
-
Reasoning changes flag 5.3x larger path errors under driving sensor noise
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
-
Manifold constraints keep preset accuracy after input saturation
Fully Actuated Manifold Constraint Based Output Feedback Control for Input-Constrained Uncertain Nonlinear Systems
-
Blind agents rotate Baoding balls 13 times in 10 seconds
roto 2.0: The Robot Tactile Olympiad
-
3D point clouds lift VLA robot success by 10%
PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
-
Multi-component risk field detects collisions earlier on benchmark tests
MC-Risk: Multi-Component Risk Fields for Risk Identification and Motion Planning
-
Swept-volume docking registers object pose to sub-millimeter precision
From swept contact to pose: Probe-aware registration via complementary-shape docking
-
Simulation feedback picks best synthetic scenes for driving models
Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
-
Joint sensors alone yield 3x faster cube rotations
Learning Robust Dexterous In-Hand Manipulation from Joint Sensors with Proprioceptive Transformer
-
Hyper-V2X estimates epistemic and aleatoric uncertainty in cooperative BEV segmentation
Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation
-
Structural latent points raise robotic task success rates
Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
-
RL with CVaR layers adapts risk for efficient crowd navigation
Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions