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
6171 storiesAn Affordable AI-Integrated Smart Cane for Multimodal Mobility Assistance of Visually Impaired Users
arXiv:2609.22277v1 Announce Type: cross Abstract: Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevat…
Industrial Kinematic Trajectory Model (IKTM): Coordinate-Free Autoregressive Generator
arXiv:2609.22173v1 Announce Type: cross Abstract: Mobility simulation supports logistics, safety, and communications planning in industrial environments such as…
Learning Beyond What Humans Can Demonstrate
arXiv:2609.24996v1 Announce Type: new Abstract: Behavior cloning for robot manipulation relies on expert demonstrations. However, for tasks that require dynamic…
DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement
arXiv:2609.24868v1 Announce Type: new Abstract: World Action Models (WAMs) jointly generate robot actions and predict future world states, transferring priors f…
PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control
arXiv:2609.24840v1 Announce Type: new Abstract: Diffusion models offer flexible motion generation, but translating this flexibility into feedback-responsive hum…
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
arXiv:2609.24815v1 Announce Type: new Abstract: Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet…
D-JEPA: A Decision-Aligned Latent World Model
arXiv:2609.24749v1 Announce Type: new Abstract: Latent world models predict the consequences of actions, but accurate prediction does not guarantee that latent …
SPARSER: Sparse Variable Projection by Exploiting Separable Structure in Robotic Perception
arXiv:2609.24708v1 Announce Type: new Abstract: Robotic perception often requires solving large nonlinear least-squares (NLS) problems. While sparsity has been …
What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior
arXiv:2609.24576v1 Announce Type: new Abstract: Modern Vision-Language Navigation (VLN) models rely mostly on pre-trained large Vision-Language Models (VLMs) to…
MIRA: Real-Time Full-Duplex Human-Robot Interaction for Embodied Companions
arXiv:2609.24547v1 Announce Type: new Abstract: Real-time embodied companion interaction requires a robot to infer user intent from streaming speech, generate t…
A Monolithic Force-Proprioception Soft Acutuator Enabled by Single-Material 3D printing
arXiv:2609.24499v1 Announce Type: new Abstract: Pneumatic proprioceptive actuators integrate actuation and sensing for soft robots that attract interest due to …
Zeva-Ego: Egocentric Mid-Training with In-Context Causal Learning for Robot Manipulation
arXiv:2609.24411v1 Announce Type: new Abstract: Egocentric video offers a scalable source of physical interaction experience, yet translating it into robot-exec…
Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors
arXiv:2609.24385v1 Announce Type: new Abstract: Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularl…
BayesianGS-SLAM: Uncertainty-Aware Neural Rendering SLAM via Probabilistic Formulation
arXiv:2609.24140v1 Announce Type: new Abstract: Neural-rendering-based SLAM relies on rendered RGB-D residuals for camera tracking and map optimization, but the…
Phrase-Level Robotic Guqin Performance: Bimanual Motion Planning and Audio-Tactile Interaction Monitoring
arXiv:2609.24133v1 Announce Type: new Abstract: Recent advances in humanoid robotics and embodied intelligence have enabled robots to perform increasingly compl…
ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation
arXiv:2609.24124v1 Announce Type: new Abstract: Active perception and manipulation are crucial for robots to interact with complex scenes. Existing benchmarks s…
Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning
arXiv:2609.24033v1 Announce Type: new Abstract: Reliable action evaluation in contact-rich manipulation requires looking beyond the current observation to futur…
Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation
arXiv:2609.23968v1 Announce Type: new Abstract: Humanoid robots are expected to perform diverse human-level tasks in daily environments, many of which require p…
Topology-Informed Visual Prompting For Vision Language Action Policies
arXiv:2609.23944v1 Announce Type: new Abstract: Vision-language-action (VLA) policies can struggle with manipulation tasks with complex obstacle geometries due …
MR-SPITE: Accelerating Multi-Robot Conflict Scans via Hierarchical Swept-Volume Approximations
arXiv:2609.23928v1 Announce Type: new Abstract: Conflict scanning over synchronized robot paths requires detailed collision checking, potentially across every r…
HumynexSurg-1: A Curated Expert Liposuction Dataset
arXiv:2609.23885v1 Announce Type: new Abstract: Robot foundation models learn manipulation from large demonstration corpora, but surgery is missing from those c…
ContactDP: Contact-Guided Diffusion Policy for Tight Insertion Tasks
arXiv:2609.23800v1 Announce Type: new Abstract: High-precision connector insertion remains challenging for robotic systems due to tight mechanical tolerances, p…
UniPoint: Unified Point-Level Sensor Fusion for Humanoid Locomotion Across Challenging Terrains
arXiv:2609.23666v1 Announce Type: new Abstract: Open-world deployment requires humanoid robots to cross highly heterogeneous terrain safely, with perception tha…
Cognitive Action Reasoning for Proactive Robots from Human-Centered Multimodal Observations
arXiv:2609.23486v1 Announce Type: new Abstract: Robots operating in human-centered environments are typically designed to execute explicit instructions, and mos…
STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots
arXiv:2609.23483v1 Announce Type: new Abstract: Humanoid loco-manipulation faces two prominent limitations: controllers using continuous velocity commands canno…
Receding-Horizon Pushing with Composable Object-Centric Policies
arXiv:2609.23439v1 Announce Type: new Abstract: Non-prehensile manipulation is practical for relocating large, heavy, or geometrically ungraspable objects. Yet,…
HEARTH: An Object-Centric RGB-Thermal-3D Dataset for Temperature-Aware Robot Manipulation
arXiv:2609.23418v1 Announce Type: new Abstract: Language-guided manipulation can depend on physical properties that visible appearance does not reveal. Temperat…
EmoPose: Vision-Language Model Guided Emotion-Aware Gesture Generation for Humanoid Robots
arXiv:2609.23414v1 Announce Type: new Abstract: Socially competent humanoid robots must communicate affect and intent through gesture as well as speech, yet ope…
Manipulation Feasible Navigation Among Movable Obstacles with Discrete Contact Pushing
arXiv:2609.23312v1 Announce Type: new Abstract: In environments with large movable obstacles, detour-only navigation can be inefficient or even infeasible, whil…
Shared Execution-Clock Drifting Policy for Dynamic Precision Manipulation
arXiv:2609.23305v1 Announce Type: new Abstract: Manipulation under time constraints requires both accurate actions and an execution rhythm that matches the evol…