Papers for

industrial robotics teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Modular manufacturing systems optimized faster with inverse models

Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models

Abstract: This paper presents a novel approach for data-driven self-learning control of highly flexible, modular manufacturing systems. Specifically, we employ a novel framework for model-based reinforcement learning which introduces approximate inverse process models within the training of reinforcement policies. This approach disentangles the learning of actuation dynamics and the dynamics in state space, resulting in RL-based training solely within the task space. We propose a lightweight feedforward architecture for approximate inverse models and integrate them within the policy network of standard RL algorithms. We apply the approach to a laboratory modular production testbed with heterogeneous production modules. The results underline the efficiency improvements for modular manufacturing units in terms of both performance and training speed, particularly for off-policy algorithms.

Thu 10 SeptArtificial IntelligenceMachine Learning
The gist
Modular factories can be hard to control because they have many separate parts working together in different ways. The authors introduced a new method that helps robots and machines learn better how to run these modular systems by teaching the control software how actions translate into changes. They use a special kind of learning called reinforcement learning but improve it by separating how machine actions link to results. This makes training faster and the systems perform better in practice.
Open 2609.11615v1

Federated learning improves privacy and efficiency for 6g robot intelligence

Modality-Decoupled Federated Learning for Privacy-Preserving Embodied Intelligence in 6G

Abstract: Sixth-generation (6G) wireless networks are expected to provide a key infrastructure for large-scale embodied intelligence, where heterogeneous robots collaborate through low-latency connectivity, edge intelligence, and distributed sensing. Vision-language-action (VLA) models offer a foundation by integrating visual perception, language understanding, and action generation into a unified closed-loop policy. However, training and adapting VLA models to distributed robotic agents introduce challenges in privacy protection, communication efficiency, and model heterogeneity. Existing federated learning (FL) methods overlook the intrinsic differences among vision, language, and action pathways in parameter scale, privacy exposure, update dynamics, and tolerance to compression or perturbation. To address this issue, this article proposes FedMVLA, a modality-decoupled FL framework for privacy-preserving embodied intelligence in 6G networks. FedMVLA incorporates three mechanisms: modality-aware federated aggregation (MAFA), modality-aware privacy allocation (MAPA), and modality-aware communication compression (MACO), together with a modality-sliced transport design that routes the precision-critical action stream through a protected ultra-reliable low-latency slice. A case study on federated robotic manipulation over the Third Generation Partnership Project (3GPP)-based wireless substrate, covering fading, co-channel interference, and malicious jamming, shows that FedMVLA achieves an 84.8% task success rate, exceeds FedAvg by 22.2 percentage points, sustains a widening margin when scaling to 128 clients across eight cells, and reduces the schedule-averaged per-client uplink model-update payload by 95.6% (approximately 96%), while keeping the 95th percentile (p95) of the round-critical uplink completion time near 1.5s.

Wed 9 SeptArtificial Intelligence
The gist
Connecting many robots over future 6G wireless networks lets them work together smarter, but sharing their knowledge can risk privacy and waste network resources. The authors propose FedMVLA, a new way for robots to learn together while keeping different types of information—like vision, language, and actions—separate and handled according to their needs. Their approach improves privacy protection, reduces the amount of data sent over the network, and speeds up learning. Tests show that FedMVLA helps robot teams complete tasks more successfully and efficiently, even when many devices are connected and when signals are disrupted.
Open 2609.09591v1