Learning-augmented robotic automation for real-world manufacturing

• URL: http://arxiv.org/abs/2604.22235v1
• Date: Fri, 24 Apr 2026 05:20:26 GMT
• Title: Learning-augmented robotic automation for real-world manufacturing
• Abstract summary: We present Learning-Augmented Robotic Automation, a hybrid system that integrates learned task controllers and a 3D safety monitor into conventional industrial neural.<n>We deployed the system on an electric-motor production line to automate deformable cable insertion and soldering under real manufacturing constraints.<n>With less than 20 min of real-world data per task, the system operated continuously for 5 h 10 min, producing 108 motors without physical fencing and achieving a 99.4% pass rate on product-level quality-control tests.
• Score: 12.335382654697817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Industrial robots are widely used in manufacturing, yet most manipulation still depends on fixed waypoint scripts that are brittle to environmental changes. Learning-based control offers a more adaptive alternative, but it remains unclear whether such methods, still mostly confined to laboratory demonstrations, can sustain hours of reliable operation, deliver consistent quality, and behave safely around people on a live production line. Here we present Learning-Augmented Robotic Automation, a hybrid system that integrates learned task controllers and a neural 3D safety monitor into conventional industrial workflows. We deployed the system on an electric-motor production line to automate deformable cable insertion and soldering under real manufacturing constraints, a step previously performed manually by human workers. With less than 20 min of real-world data per task, the system operated continuously for 5 h 10 min, producing 108 motors without physical fencing and achieving a 99.4% pass rate on product-level quality-control tests. It maintained near-human takt time while reducing variability in solder-joint quality and cycle time. These results establish a practical pathway for extending industrial automation with learning-based methods.

Related papers

• A Deployment Case Study in Robotic Apparel Automation: Digital Twin Integration, Interoperability, and Workforce Enablement [2.7982519003969855]
  This paper presents a deployment-oriented case study of a robotic sewing system for denim manufacturing.<n>A digital thread module parses DXF production drawings into process parameters and executable robot trajectories, reducing manual programming effort.<n>A digital twin of the workcell is used during pre-deployment to validate reach and clearance, refine layout and sequencing, evaluate operator access, and assess cycle-time compatibility with upstream and downstream tasks.
  arXiv  Detail & Related papers  (2026-06-15T00:34:58Z)
• A Robotic Testing Platform for Pipelined Discovery of Resilient Soft Actuators [63.07587517846448]
  We propose an optimization pipeline enabled by a novel testing robot capable of scanning DEA lifetime.<n>The robot integrates electro-mechanical property measurement, programmable voltage input, and multi-channel testing capacity.<n>Using it, we scanned the lifetime of Elastosil-based linear actuators across parameters including input voltage magnitude, frequency, electrode material concentration, and electrical connection filler.
  arXiv  Detail & Related papers  (2026-02-24T14:41:28Z)
• RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning [33.36533022574748]
  We present RL-100, a real-world reinforcement learning framework built on diffusion visuomotor policies trained by supervised learning.<n>We evaluate RL-100 on seven real-robot tasks spanning dynamic rigid-body control, such as Push-T and Agile Bowling.<n> RL-100 attains 100% success across evaluated trials for a total of 900 out of 900 episodes, including up to 250 out of 250 consecutive trials on one task.
  arXiv  Detail & Related papers  (2025-10-16T16:07:50Z)
• FAST: Efficient Action Tokenization for Vision-Language-Action Models [98.15494168962563]
  We propose a new compression-based tokenization scheme for robot actions, based on the discrete cosine transform.<n>Based on FAST, we release FAST+, a universal robot action tokenizer, trained on 1M real robot action trajectories.
  arXiv  Detail & Related papers  (2025-01-16T18:57:04Z)
• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• Machine Learning Meets Advanced Robotic Manipulation [48.6221343014126]
  The paper reviews cutting edge technologies and recent trends on machine learning methods applied to real-world manipulation tasks. The rest of the paper is devoted to ML applications in different domains such as industry, healthcare, agriculture, space, military, and search and rescue.
  arXiv  Detail & Related papers  (2023-09-22T01:06:32Z)
• Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning [70.70104870417784]
  Reinforcement learning (RL) algorithms hold the promise of enabling autonomous skill acquisition for robotic systems. In practice, real-world robotic RL typically requires time consuming data collection and frequent human intervention to reset the environment. In this work, we study how these challenges can be tackled by effective utilization of diverse offline datasets collected from previously seen tasks.
  arXiv  Detail & Related papers  (2022-07-11T08:31:22Z)
• An Automated Robotic Arm: A Machine Learning Approach [0.0]
  The modern industry is rapidly shifting from manual control of systems to automation. Computer-based systems, though feasible for improving quality and productivity, are inflexible to work with. One such task of industrial significance is of picking and placing objects from one place to another.
  arXiv  Detail & Related papers  (2022-01-07T10:33:01Z)
• Towards the Automation of a Chemical Sulphonation Process with Machine Learning [0.0]
  This paper presents the results of applying machine learning methods during a chemical sulphonation process. We used data from process parameters to train different models including Random Forest, Neural Network and linear regression. Our experiments showed that it is possible to predict those product quality values with good accuracy, thus, having the potential to reduce time.
  arXiv  Detail & Related papers  (2020-09-25T10:56:41Z)
• Detection and Classification of Industrial Signal Lights for Factory Floors [63.48764893706088]
  The goal is to develop a solution which can measure the operational state using the input from a video camera capturing a factory floor. Using methods commonly employed for traffic light recognition in autonomous cars, a system with an accuracy of over 99% in the specified conditions is presented.
  arXiv  Detail & Related papers  (2020-04-23T14:26:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.