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
6273 storiesHierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models
arXiv:2608.24042v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models pretrained on large-scale robot datasets provide a strong foundation f…
NeurRAFT: Robot Motion Planning via Anchor-Level Flow Matching with Clearance-Aware Preference Tuning
arXiv:2608.24026v1 Announce Type: new Abstract: Recent end-to-end neural motion planners generate trajectories from raw sensor observations, avoiding the privil…
Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency
arXiv:2608.23831v1 Announce Type: new Abstract: While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the…
Concept-Guided Exploration: Building Persistent, Actionable Scene Graphs
arXiv:2608.23650v1 Announce Type: new Abstract: The perception of 3D space by mobile robots is rapidly moving from flat metric grid representations to hybrid me…
DreamLedger: Execution-Settled Credit Files for World-Model Imagination in Robot Decision Loops
arXiv:2608.23863v1 Announce Type: new Abstract: Robots are beginning to act on world-model predictions, yet reliability is still expressed through instantaneous…
Sensorless damage-safe grasping
arXiv:2608.23983v1 Announce Type: new Abstract: Robotic fruit harvesting must hold produce securely without bruising it, yet compression stiffness varies severa…
Bridging Teacher Expectations and Robot Learning via Coupling Dynamics
arXiv:2608.23994v1 Announce Type: new Abstract: Human-robot teaching focuses on enabling nontechnical experts to customize robots according to their needs after…
Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings
arXiv:2608.24039v1 Announce Type: new Abstract: Manufacturing process planning transforms heterogeneous design information into coherent manufacturing decisions…
Trajectory-Level Continuous Action Representation for Robotic Manipulation
arXiv:2608.24111v1 Announce Type: new Abstract: We propose CAT, a trajectory-level continuous action representation framework for robotic manipulation. Existing…
VLANeXt: Recipes for Building Strong VLA Models
arXiv:2602.18532v3 Announce Type: replace-cross Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveragin…
Observability Engineering: From Measurement to Information Generation in Active Sensing Systems
arXiv:2602.13554v2 Announce Type: replace-cross Abstract: This article develops a four stage observability engineering framework for interaction driven sensing.…
Adaptive Multi-Mode Out-of-Distribution Detection for Trajectory Prediction in Autonomous Vehicles
arXiv:2509.13577v3 Announce Type: replace-cross Abstract: Trustworthy trajectory prediction grounds autonomous vehicle (AV) safety, yet deployed models inevitab…
Topology-Aware Decision Making for Multi-Session Localization and Mapping
arXiv:2602.17226v2 Announce Type: replace Abstract: Operating in previously visited environments is becoming increasingly crucial for autonomous systems, with d…
EllipseLIO: Adaptive LiDAR Inertial Odometry with an Ellipsoid Representation
arXiv:2605.21150v2 Announce Type: replace Abstract: LiDAR Inertial Odometry (LIO) is a critical component for many mobile robots that need to navigate without r…
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
arXiv:2605.11048v2 Announce Type: replace Abstract: Existing imitation learning methods enable robots to interact autonomously with the physical environment. Ho…
Latent Dynamics-Aware OOD Monitoring for Trajectory Prediction with Provable Guarantees
arXiv:2603.14603v2 Announce Type: replace Abstract: In safety-critical Cyber-Physical Systems (CPS), trajectory prediction guides downstream planning and contro…
Look as You Leap: Planning Simultaneous Motion and Perception for High-DOF Robots
arXiv:2509.19610v3 Announce Type: replace Abstract: Most common tasks for robots in dynamic spaces require that the environment is regularly and actively percei…
Design and Evaluation of a Compliant Quasi Direct Drive End-effector for Safe Robotic Ultrasound Imaging
arXiv:2410.03086v2 Announce Type: replace Abstract: Robot-assisted ultrasound scanning promises to advance autonomous and accessible medical imaging. However, e…
$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks
arXiv:2608.24743v1 Announce Type: cross Abstract: Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neura…
X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis
arXiv:2608.24563v1 Announce Type: cross Abstract: Imaging factor disentanglement in text-to-image generation aims to independently control image acquisition pro…
Variance-Guided Spatial Attention Fusion for Robust End-to-End Driving under Asymmetric Sensor Degradation
arXiv:2608.24366v1 Announce Type: cross Abstract: End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines re…
Event-Based Motion Estimation via Oriented Distance Fields
arXiv:2608.24223v1 Announce Type: cross Abstract: Event-based motion estimation is central to tasks that demand high temporal resolution and robustness to fast …
Trusted Polytopic Action Sets for Fast Planning in Underactuated Systems
arXiv:2608.24019v1 Announce Type: cross Abstract: Underactuated systems pose a challenge for convex motion planning because their dynamically feasible motions l…
Energy-Aware Performance Evaluation of Nonlinear Mechatronic Systems Under Matched-Tracking Conditions
arXiv:2608.23578v1 Announce Type: cross Abstract: Trajectory-tracking metrics such as root-mean-square error (RMSE), overshoot, and settling time are widely use…
GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models
arXiv:2608.24714v1 Announce Type: new Abstract: World-Action Models (WAMs) jointly learn future visual prediction and action generation, using video dynamics as…
VIP: Variation-based Iterative-learning Planning for Robotic Navigation
arXiv:2608.24618v1 Announce Type: new Abstract: Over the past decade, autonomous robotic systems have been increasingly deployed in applications such as surveyi…
Gripper-aware Vision Language Action Models
arXiv:2608.24603v1 Announce Type: new Abstract: Vision language action models (VLAs) have advanced general purpose robotic grasping and manipulation by enabling…
TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks
arXiv:2608.24101v1 Announce Type: new Abstract: Robot actions are inherently embodiment-specific and only weakly aligned with image-space visual changes, limiti…
Safety-aware Model Predictive Path Integral Control with Signal Temporal Logic
arXiv:2608.23972v1 Announce Type: new Abstract: Safety-aware motion planning remains a challenge in robotics, especially when missions are time-critical and are…
Interpreting Control Latents for System Identification via Conditional Flow Matching
arXiv:2608.23887v1 Announce Type: new Abstract: Latent-conditioned adaptive policies can control robots across changing dynamics, but their learned latents rema…