UR5e Research

Articles

Research

  • OpenTac: An Open Ecosystem for Customizable, Scalable, and Transferable 3D Tactile Sensing - 2026-10-22 - Research Publication - OpenTac combines customizable resistive tactile skins with CAD generation, simulation, sensor transfer and adaptive acquisition. The design estimates normal and shear forces from structured bumps over taxel arrays.… - source: arxiv.org
  • FR-VLA: Implicit Force Reasoning VLA for Contact-Rich Manipulation - 2026-10-19 - Research Publication - FR-VLA uses implicit force reasoning for contact-rich manipulation. Five tasks are evaluated on UR5e and UR3e robots with force/torque information and external and wrist-mounted cameras. - source: arxiv.org
  • RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models - 2026-10-19 - Research Publication - RoboValue evaluates robotic value models across task understanding, progress tracking, failure and recovery reasoning, and value consistency. It combines15simulated and20real-world manipulation tasks, testing zero-shot and… - source: arxiv.org
  • CusADi2: Latency-Optimized Batch Computation of Robot Kinematics, Jacobians, and Hessians on the GPU - 2026-10-18 - Research Publication - CusADi2 reduces batch-computation latency by parallelizing both across and within robot-model evaluations on GPUs. The authors benchmark kinematics, Jacobians and Hessians across67 MuJoCo Menagerie robots and report lower… - source: arxiv.org
  • ContactBench 1.0: A Benchmark for Everyday Contact-Rich Robotic Manipulation - 2026-10-17 - Research Publication - ContactBench 1.0 organises everyday contact-rich manipulation into36 reference tasks and more than 40 printable object assets. It combines physical mechanisms with corresponding simulation models and evaluates six selected… - source: arxiv.org
  • LABIT: Long-Horizon Robotic Assembly Benchmark for Industrial Tasks - 2026-10-12 - Research Publication - LABIT benchmarks long-horizon industrial assembly through standardized parts, sequential assembly operations, a complexity taxonomy and quality-aware metrics. Baselines use traditional force-position control; the released… - source: arxiv.org
  • FlowVLA: Enabling World Dynamics Understanding through Pluggable 3D Flow Learning - 2026-10-12 - Research Publication - FlowVLA uses reconstructed 3D flow during training to supervise action-relevant dynamics. It adds point-level and tool-centre-point supervision without requiring additional 3D sensors or changing the inference-time… - source: arxiv.org
  • OATH: Object-Agnostic Tracking for Dexterous Hands, Enabling Rapid Physics-based Retargeting - 2026-10-09 - Research Publication - OATH uses a contact-conditioned residual policy to retarget human grasping trajectories to dexterous hands across unseen objects. Multiply Labs and university researchers report 58% held-out and 54% unseen-object… - source: arxiv.org
  • On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation - 2026-07-11 - Research Publication - A configured UR5e inserted bolts, sorted a target bolt and press-fit a bearing in physical VLA trials. - source: arxiv.org
  • Context-Aware Force Estimation for Deformable Tool Manipulation in Robotic Environmental Swabbing via Few-Shot Continual Adaptation - 2026-07-08 - Research Publication - A physical UR5e estimates deformable swab contact force across nine tool-surface conditions. - source: arxiv.org
  • Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts - 2026-07-01 - Research Publication - DART evaluates simulated cross-embodiment VLA transfer from Panda to UR5e. - source: arxiv.org
  • A Multimodal Manufacturing Safety Chatbot: Knowledge Base Design, Benchmark Development, and Evaluation of Multiple RAG Approaches - 2025-11-14 - Research Publication - The authors introduce a multimodal chatbot powered by large language models that meets these design requirements. - source: arxiv.org
  • Using Knowledge Representation and Task Planning for Robot-agnostic Skills on the Example of Contact-Rich Wiping Tasks - 2023-08-27 - Research Publication - To achieve that in this case study, their approach needs to address different kinematics, gripper types, vendors, and fundamentally different control interfaces. - source: arxiv.org
  • Generalized Object Search - 2023-01-24 - Research Publication - In support of this argument, I develop methods and systems for (multi-)object search in 3D environments under uncertainty due to limited field of view, occlusion, noisy, unreliable detectors, spatial correlations between… - source: arxiv.org
  • Learning to Play Cup-and-Ball with Noisy Camera Observations - 2020-07-19 - Research Publication - The study presents a learning model based control strategy for the cup-and-ball game, where a Universal Robots UR5e manipulator arm learns to catch a ball in one of the cups on a Kendama. - source: arxiv.org

View UR5e overview