Multi-task scheduling of self-driving laboratories under scientific constraints

The past, present and future of self-driving laboratories

The evolution of SDLs is charts their evolution from bespoke systems to interoperable platforms, highlighting challenges in scalability, generalizability and data provenance, and outlining pathways towards networked, trustworthy infrastructures enabling collective scientific superintelligence.

Robustness-Aware Physical AI for Multi-Functional Humanoid Robot Team Concurrency Control Under Imperfect Digital Twin Information

Humanoid robots are emerging as flexible robotic resources for autonomous manufacturing systems, where different types of tasks must be assigned to suitable robots while shared production resources are coordinated effectively. However, realistic manufacturing environments involve dynamic task arrivals, event-driven priority changes, heterogeneous robot capabilities, and shared-resource contention. In addition, digital twin-based scheduling may rely on state information that is delayed or uncertain, which can reduce the reliability of scheduling decisions. To address this issue, this paper extends the previously proposed deep reinforcement learning-based concurrency control (DRLCC) framework for robustness-aware scheduling and shared-resource control of a multi-functional humanoid robot team. The extended framework integrates capability-aware task assignment, feasibility-based action masking, and priority ceiling protocol (PCP)-based shared-resource coordination under delayed and uncertain digital twin observations. The framework is evaluated in a humanoid-based autonomous manufacturing scenario using performance indicators including task completion, urgent-task delay, resource contention, humanoid utilization, and robustness degradation under imperfect state feedback. Compared with the greedy ceiling-based baseline, DRLCC reduces high-priority task delay by approximately 10.9%, priority inversions by 42.1%, average waiting time by 73.8%, average block count by 74.0%, and temporary infeasible events by 73.5%, while maintaining comparable humanoid utilization. The robustness analysis further shows that overall task-completion performance remains stable under imperfect digital twin feedback, although coordination-level metrics are more sensitive to observation uncertainty and delay. These results suggest that the extended DRLCC framework can support robustness-aware humanoid robot team scheduling in autonomous manufacturing environments where digital twin observations are delayed or uncertain.

LUCID: An Agentic AI Framework on Digital-Twin in the Loop for QoS-Guaranteeing Robotic Control

LUCID is presented, an LLM-agent--orchestrated, uplink-aware cloud-robotics pipeline that moves TP--RRM from solving a fixed formulation to dynamically orchestrating optimization problem schemas within a DITL environment and robustly adapts to changing intents, active-robot counts, and scenes.

Generalizable Multi-Agent Planning From Signal Temporal Logic Specifications Via Diffusion

Multi-agent systems in the real-world (e.g., drone swarms, autonomous cars, warehouse robots) must satisfy rich, temporal tasks while avoiding collisions. Signal Temporal Logic (STL) elegantly encodes such objectives, but current STL planning methods face critical limitations. State-of-the-art optimization-based approaches can handle arbitrary STL specifications but struggle with scalability, becoming computationally impractical as the number of agents grows. Learning-based methods efficiently handle a large number of agents with rapid planning times but fare poorly when deployment-time objectives differ from those used during training, and do not support planning tasks that require different specifications to be ascribed to different agents (i.e., heterogeneity) or team-level specifications requiring coordination of multiple agents. This fundamental trade-off between generalizability and scalability presents a challenge for realizing multi-agent STL planning algorithms in practice. To overcome this challenge, we introduce a new diffusion method for multi-agent planning with STL specifications. Using a differentiable approximation of STL, we integrate the STL gradient in the denoising process, making our approach generalizable to novel formulas whose predicates are placed anywhere within the goal region covered during training, while achieving the same scalability as existing learning-based methods. Our method supports heterogeneous specifications, and by using diffusion models, naturally enhances plan diversity, thereby significantly reducing safety-related violations (e.g., collisions) among agents. A detailed evaluation study justifies the utility of STL-guided diffusion-based multi-agent planners for constructing generalizable, scalable, and diverse plans. Videos and code are available at https://www.jeappen.com/diff-ma-stl/ and https://github.com/jeappen/diff-ma-stl .

Multi-Agent System-driven Digital Twins for predictive maintenance: architectures, technologies and open research challenges

This systematic review explores the intersection between Multi-Agent Systems and Digital Twins, with a particular focus on predictive maintenance applications in resource-constrained contexts and reveals that, despite significant progress, no existing system offers an integrated embedded-distributed hierarchical solution that simultaneously meets the requirements of Industry 5.0.

Adaptive Software Architecture for Managing Autonomous Robotic Logistics in Contested Environments