archive
Every paper Pith has read. Search by title, abstract, or pith.
2900 papers in cs.RO · page 3
-
Small ensemble beats giant LLMs at robot skill prediction
To Select or not to Select, that is the Question: Distilling Robot Skill Prediction into a Small Ensemble
-
Adaptive epsilon-MPC navigates uneven terrain with 94% success
A Terrain-Adaptive epsilon-Constraint MPC for Uneven Terrain Kinodynamic Planning
-
YOLOv11 detects military targets in synthetic thermal and night drone images
Comparative Analysis of Military Detection Using Drone Imagery Across Multiple Visual Spectrums
-
EllipseLIO cuts odometry error 38 percent with adaptive ellipsoids
EllipseLIO: Adaptive LiDAR Inertial Odometry with an Ellipsoid Representation
-
This paper develops a safety filter for smoothed implicit contact dynamics by bounding…
Safety-Critical Control for Smoothed Implicit Contact Dynamics
-
Dual modules let humanoids do 3D tasks without robot training data
Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum
-
Empirical steering fit beats learning methods in racing tests
Benchmarking Empirical and Learning-Based Approaches for Feedforward Steering Control in Autonomous Racing
-
Fusing two anomaly scores cuts calibration error 37% on physical racing car
Anomaly-Informed Confidence Calibration for Vision-Based Safety Prediction
-
0.5B driving model matches 7B models by adding future visual states
Grounding Driving VLA via Inverse Kinematics
-
Robots match humans in stress levels during elder health surveys
Perception of Social Robots as Communication Partners in Healthcare for Older Adults
-
SOFA model adds soft morphing arms to quadrotor
Modeling and Control of a Pneumatic Morphing Soft Quadrotor based on the SOFA Framework for Dynamic Soft Robotic Simulation
-
Soft quadrotor keeps standard controls while arms morph
Modeling and Control of a Pneumatic Morphing Soft Quadrotor based on the SOFA Framework for Dynamic Soft Robotic Simulation
-
Influence scores cut fasteners to simplify robotic disassembly
Component Influence-Driven Fastener Reduction for Robotic Disassemblability-Aware Design Simplification
-
LiteViLNet reaches 96.36% MaxF with 14M parameters at 164 FPS
LiteViLNet: Lightweight Vision-LiDAR Fusion Network for Efficient Road Segmentation
-
Wires anchor robot body to free legs for tasks
WiXus: A Wheeled-Legged Robot with Wire-Driven Environmental Utilizing to Integrate Mobility and Manipulation
-
STEAM raises decentralized MAPF success rates up to 60%
STEAM: A Training-Free Congestion-Aware Enhancement Framework for Decentralized Multi-Agent Path Finding
-
Tool generates 150 variable underground worlds for robot tests
SubTGraph: Large-Scale Subterranean Environment Synthesis with Controllable Topological Variability for Robotic Autonomy Validation
-
Decoupled base and hand motion lifts mobile imitation success
Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation
-
Hypernetwork generates full robot policies from instructions alone
DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation
-
Joint scale and pose solver hits 2.9 degree knee error on fluoroscopy
SmoCap: Unified Scale-Pose Canonicalization with Proxy-Mapped Trust-Region QP
-
Patch alignment spots changes in free-motion videos
VSCD: Video-based Scene Change Detection in Unaligned Scenes
-
Latent trajectories turn visual demos into robot subgoals
Demo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
-
Quantum spiking RL reaches 99% success in navigation
Q-SpiRL: Quantum Spiking Reinforcement Learning for Adaptive Robot Navigation
-
Constraint manifolds with corners solve mixed-constraint optimization
CMC-Opt: Constraint Manifold with Corners for Inequality-Constrained Optimization
-
Low-cost benchmark lets labs replicate VLA robot tests anywhere
VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
-
New guidance resolves gradient conflicts in flow models
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
-
Compact Gaussian prefix supplies 3D supervision for robot policies
GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation
-
Semantic occlusion model cuts track-start delay in crowded driving scenes
A Semantic and Occlusion-Aware GM-PHD Filter
-
Joint action-predicate model enables zero-shot robot skill composition
Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition
-
RL method produces ready-to-bend pipes for aeroengines
Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines
-
TTR metrics unify priority and safety for aerial vehicle merging
Time-To-Reach Separation and Safety Filtering for Safe, Fair, and Efficient Multi-Agent Coordination
-
Vision model separates content from style to assure landing safety
Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
-
Intent-first V2V supports drone tactical separation in moderate densities
Intent-First Aerial V2V for Tactical Coordination and Separation: Protocol and Performance Under Density and Disturbance
-
Risk metric turns into barrier that keeps robots safe in uncertain maps
Conflict-Aware Active Perception and Control in 3D Gaussian Splatting Fields via Control Barrier Functions
-
Truss robot keeps 69% workspace after motor fails
Fault-Tolerant, Rigidity-Preserving Control of Inflatable Truss Robots
-
Weighted clusters plus pruning give flexible speed-accuracy control in VPR
Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning
-
Robotic planners say yes to most impossible commands
The Yes-Man Syndrome: Benchmarking Abstention in Embodied Robotic Agents
-
Leg odometry cuts elevation drift to under 30 cm in robot SLAM
Enhancing Graph-Based SLAM in GNSS-Denied environments by leveraging leg odometry
-
Optimal transport attention reaches 100 percent success on tight peg-in-hole
Spacetime Optimal-Transport Attention for Visuo-Haptic Imitation Learning of Contact-Rich Manipulation
-
Robots give homebound K-12 students classroom mobility
Multi-Week, In-Class Deployments of Telepresence Robots With Four Homebound K-12 Students: Benefits, Challenges, and Recommendations
-
Workspace decomposition cuts multi-robot planning time by 10x
Scalable Multi-robot Motion Planning via Hierarchical Subproblem Expansion and Workspace Decomposition Refinement
-
Tactile MPC follows contours directly in feature space
VBT-MPC: Vision-Based Tactile MPC for Contour Following
-
Bigger 3D models trained on 50M driving scenes top Waymo leaderboard
STELLAR: Scaling 3D Perception Large Models for Autonomous Driving
-
Human videos scale humanoid loco-manipulation without custom rewards
SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework
-
Nudges to learnable states yield 7x larger skill gains than standard AI sharing
Proximal State Nudging: Reducing Skill Atrophy from AI Assistance
-
Backward reachable sets ensure collision-free satellite paths
Hamilton--Jacobi Reachability for Spacecraft Collision Avoidance
-
3D optimization yields high-bending pneumatic actuators
Topology-Optimized Pneumatic Soft Actuator: Design and Experimental Validation
-
Moderate noise raises LLM agent success 2.85-fold on puzzle task
Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving
-
Staged analysis improves LLM recovery of ROS 2 architectures
Towards LLM-Assisted Architecture Recovery for Real-World ROS~2 Systems: An Agent-Based Multi-Level Approach to Hierarchical Structural Architecture Reconstruction
-
Four photodiodes replace cameras for robot odometry
Minimalist Visual Inertial Odometry