Research
Frontier robotics research: arXiv cs.RO papers, embodied AI, VLA models, manipulation, navigation and learning systems.
Frontier robotics research: arXiv cs.RO papers, embodied AI, VLA models, manipulation, navigation and learning systems.
Latest in Research
4787 storiesThe Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
arXiv:2608.22301v1 Announce Type: new Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever t…
MotionDLO: Hybrid Event- and Frame-Based Tracking of Deformable Linear Objects
arXiv:2608.22398v1 Announce Type: new Abstract: Reliably tracking moving deformable linear objects (DLOs) while simultaneously ensuring robustness, accuracy, an…
LD4WAM: Learning Latent Dynamics from Human Videos for World Action Models
arXiv:2608.22403v1 Announce Type: new Abstract: Human video is playing an increasingly central role in training World Action Models (WAMs), owing to its diversi…
Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking
arXiv:2608.22419v1 Announce Type: new Abstract: Query-based Vision-Language-Action (VLA) models offer low-latency inference that is attractive for bimanual robo…
EMPIRE: Explicit Manipulation Planning as a Learnable Intermediate Representation for Egocentric Hand-Motion Forecasting
arXiv:2608.22449v1 Announce Type: new Abstract: Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive system…
What is the effect of running-specific prostheses on long jumps? Optimization-based prediction and analysis using biomechanical models
arXiv:2608.22507v1 Announce Type: new Abstract: Long jumpers with below the knee amputation (BKA) that take off from their running-specific prosthesis (RSP) imp…
WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning
arXiv:2608.22591v1 Announce Type: new Abstract: Robot policies receive heterogeneous observations at each decision step, yet sequence models differ in how they …
Enhancing Sim2Real Transfer for Torque-Controlled Robots through Real2Sim Dynamics Estimation and Reinforcement Learning
arXiv:2608.22629v1 Announce Type: new Abstract: Transferring reinforcement learning policies from simulation to Real-World robots remains a major challenge, par…
Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs
arXiv:2608.22657v1 Announce Type: new Abstract: Agentic AI frameworks interpret open-ended task goals and decompose them into multi-step plans. Richer informati…
Exact Finite-Length Theory of Uniform Car Parking: Spatial Laws, Absorption, and Aggregation
arXiv:2608.22671v1 Announce Type: new Abstract: The uniform car-parking process is the one-dimensional random sequential adsorption of unit cars on a segment of…
VikPath: A Vision Kansformer Framework for Effective Obstacle Avoidance in Self-Supervised Pathfinding
arXiv:2608.22675v1 Announce Type: new Abstract: Pathfinding is a fundamental problem in artificial intelligence and autonomous systems. Traditional heuristic-ba…
RACO: Reliability-Aware Coarse-Goal Optimization for Inspection-Oriented UAV Vision-Language Navigation
arXiv:2608.22678v1 Announce Type: new Abstract: UAV vision-language navigation (UAV-VLN) is commonly evaluated as goal reaching, but inspection-oriented deploym…
Physics Filtering Favors the Generalization of Robot Learning
arXiv:2608.22701v1 Announce Type: new Abstract: Living organisms exhibit extraordinary adaptability to unseen environments through their intrinsic physical stru…
Reproducible Vision-Guided 6-DoF Robotic Manipulator with a Mixed Stepper-Driver Architecture and Browser-Native Control
arXiv:2608.22799v1 Announce Type: new Abstract: We present the NeuralNexus Arm, an open, low-cost 6-DOF robotic manipulator built by an undergraduate engineerin…
Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation
arXiv:2608.22800v1 Announce Type: new Abstract: Ensuring reliability in uncertain environments remains difficult for long-horizon robotic manipulation. End-to-e…
UniMem: Unifying Multimodal Memory and Control for Vision-Language-Action Models
arXiv:2608.22869v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning …
InstructMove: A Text-Indispensable Benchmark for Instruction-Following Manipulation
arXiv:2608.22990v1 Announce Type: new Abstract: Vision-language-action (VLA) models have made general-purpose robot manipulation increasingly plausible by condi…
Switched Turn-based Adaptive Source Seeking Strategy using Estimation and Information-driven Direction of Improvement
arXiv:2608.23068v1 Announce Type: new Abstract: Source seeking arises in applications such as gas leak localization, radiation monitoring, and environmental sur…
Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning
arXiv:2608.23100v1 Announce Type: new Abstract: Robot co-design via bi-level optimization couples within-lifetime controller learning for fitness evaluation wit…
Pointing-VLA: Typed Spatial Grounding Interfaces for Vision-Language-Action Manipulation
arXiv:2608.23138v1 Announce Type: new Abstract: Vision-language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or op…
Spinning Quadrotor: Hover Thrust Augmentation with Passive Lifting Surfaces
arXiv:2608.23163v1 Announce Type: new Abstract: Conventional multirotor aerial vehicles actively suppress yaw rotation during hover, expending power to maintain…
Guided Riemannian Optimization (GuRO): Bridging Model Predictive Control and Decision Transformers
arXiv:2608.23204v1 Announce Type: new Abstract: Decision-making in high-dimensional, nonlinear systems remains a central challenge in robotics. While model-base…
Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation
arXiv:2608.23224v1 Announce Type: new Abstract: Retrieval can efficiently and effectively augment a frozen vision--language--action (VLA) policy without retrain…
Design of a Biomimetic Joint-Covering Skin with Tissue-Like Structure to Enhance Proprioception in a Musculoskeletal Humanoid
arXiv:2608.23304v1 Announce Type: new Abstract: Proprioception in musculoskeletal humanoids is typically estimated primarily from muscle sensing, while the role…
ROS2SmolVLA: Enabling Small Vision-Language-Action Models for Integration into Industrial-Grade Lightweight Robots
arXiv:2608.23320v1 Announce Type: new Abstract: Industrial demand changes the paradigms of production. Due to smaller batch sizes and more variations in product…
OptiSight: Bridging Semantic Reasoning and Geometric Control for Embodied Navigation
arXiv:2608.23354v1 Announce Type: new Abstract: Autonomous indoor navigation requires both semantic understanding and precise geometric control. We propose Opti…
Reward-Free Continual Adaptation for Resilient Space Robots
arXiv:2608.23452v1 Announce Type: new Abstract: Space robots operate in extreme environments where hardware degradation can critically compromise traditional co…
Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models
arXiv:2608.23478v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders ar…
Retrieval-grounded robot program generation and simulation-based correction via Model Context Protocol
arXiv:2608.21417v1 Announce Type: cross Abstract: Flexible manufacturing requires industrial robots to be reprogrammed rapidly as product variants change. This …
Agentic AI for Safety-critical Multi-drone Systems: Challenges and Opportunities
arXiv:2608.21444v1 Announce Type: cross Abstract: Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) a…