UR5e
About
About UR5e
UR5e is a six-axis arm with joint torque sensing, a compact base and an operating envelope suited to individual machines and workstations. Its wrist can carry grippers, screwdrivers, dispensers, cameras and test equipment for repeated handling or process motions. Configurable limits for speed, force, momentum and workspace support collaborative deployment where the complete application satisfies the required safety assessment.
Users create tasks through PolyScope and add third-party tools through URCaps that expose device functions within the robot program. Industrial communications and controller I/O connect the arm to machine tools, conveyors, fixtures and plant systems. Universal Robots supplies UR5e through distributors and integrators for flexible automation cells that may be redeployed as production requirements change.
Capabilities
Source-backed capabilities
- Robotic assembly
Claimed - Position and join components during collaborative assembly. - environment: Collaborative manufacturing workcells
Source - Machine tending
Claimed - Load workpieces into a machine and remove completed parts. - environment: Collaborative manufacturing workcells
Source - Material handling
Claimed - Move parts between fixtures in a manufacturing cell. - environment: Collaborative manufacturing workcells
Source - Robotic inspection
Claimed - Present or scan parts during a quality-inspection workflow. - environment: Collaborative manufacturing workcells
Source
Observed use
Exact-product configurations are shown without inferring supply, purchase, customer status, standard fit, deployment or partnership.
- HABILIS Brain 0
Research Experiment - Controlled By - Physical - Universal Robots UR5e was used in Tommoro HABILIS Brain 0 manipulation demonstrations.
Source - GelSight Mini
Research Experiment - Mounted - Physical - Four ContactBench tasks use custom UR5e gripper fingers equipped with GelSight Mini sensors.
Source - WSG50 gripper; exact50-110 variant unspecified
Research Experiment - Mounted - Physical - ContactBench uses a WSG50 parallel-jaw gripper on UR5e, with task-specific tactile or Fin-Ray fingers.
Source - Observed configuration
Research Experiment - Mounted - Physical - ContactBench physical experiments use a RealSense D435i wrist camera on a UR5e.
Source - D455
Research Experiment - Connected - Physical - UR5e was evaluated with RealSense D455 providing the third-person camera view.
Source - RealSense D405
Research Experiment - Mounted - Physical - UR5e was evaluated with RealSense D405 mounted at the wrist.
Source - Intel RealSense D435i cameras
Research Experiment - Tested With - Physical - FlowVLA’s physical evaluation uses a UR5e arm with two Intel RealSense D435i cameras.
Source - Schaeffler Group USA manufacturing cell configuration
Operational - Mounted - Physical - Schaeffler Group USA manufacturing cell uses UR5e in the configuration documented by Universal Robots.
Source - FT-Produktion machine-tending cell configuration
Operational - Mounted - Physical - FT-Produktion machine-tending cell uses UR5e in the configuration documented by Universal Robots.
Source - Vitesco Technologies manufacturing cell configuration
Operational - Mounted - Physical - Vitesco Technologies manufacturing cell uses UR5e in the configuration documented by Universal Robots.
Source - Fluidics Instruments operating configuration
Operational - Mounted - Physical - Fluidics Instruments used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - AIM Processing operating configuration
Operational - Mounted - Physical - AIM Processing used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Schneider Electric Belgium operating configuration
Operational - Mounted - Physical - Schneider Electric Belgium used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Go Fast Campers operating configuration
Operational - Mounted - Physical - Go Fast Campers used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Toolcraft operating configuration
Operational - Mounted - Physical - Toolcraft used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Olympus operating configuration
Operational - Mounted - Physical - Olympus used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Magneti Marelli operating configuration
Operational - Mounted - Physical - Magneti Marelli used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - DWD Group operating configuration
Operational - Mounted - Physical - DWD Group used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Coty Cosmetics operating configuration
Operational - Mounted - Physical - Coty Cosmetics used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Albrecht Jung operating configuration
Operational - Mounted - Physical - Albrecht Jung used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - Andrew Pearce Bowls operating configuration
Operational - Mounted - Physical - Andrew Pearce Bowls used Universal Robots UR5e in an operating configuration documented by Universal Robots.
Source - SIMP Production configuration
Operational - Mounted - Physical - Emanor integrated a UR5e gluing and assembly cell at SIMP Production.
Source - Repack-S configuration
Operational - Mounted - Physical - Isycod deployed a UR5e across two production applications at Repack-S.
Source - VCN Industries configuration
Operational - Mounted - Physical - Archytas Robotics integrated a UR5e into VCN Industries medical-part engraving cell.
Source
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. Researchers fabricate more than thirty sensor layouts and evaluate feedback control and manipulation learning on four physical robot embodiments.
Source - 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 - 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 one-shot feedback under embodiment and environment shifts.
Source - 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 latency at batch sizes64–4096 than evaluated alternatives.
Source - 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 tasks on a UR5e.
Source - 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 MuJoCo implementation includes robot and assembly-part assets.
Source - 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 architecture.
Source - 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 trajectory recovery in DexYCB simulation, plus open-loop playback on a UR5e with Wuji Hand 2.
Source - 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 - 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 - 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 - 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 - 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 - 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 objects, and possibly ambiguous spatial language (e.g., "The red car is behind Chase Bank").
Source - 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
Resources
Media library
- UR5e operating-power reference
image · Universal Robots
Source - UR5e payload curve
image · Universal Robots
Source - UR5e footprint diagram
image · Universal Robots
Source
Official UR5e product documentation with exact technical diagrams and manufacturer imagery for the light-payload e-Series cobot.
- Universal Robots UR5e product reference
WEB · UR5e collaborative robot · Universal Robots
Source - UR5e technical datasheet
PDF · UR5e technical specification · Universal Robots
Source - UR5e PolyScope 5 user manual
PDF · UR5e, PolyScope 5.25.1 · Universal Robots
Source - UR5e online hardware and safety manual
WEB · UR5e hardware and safety reference · Universal Robots
Source