Abstract--Recent years have witnessed a growing interest in automating labor-intensive and complex activities, i.e., those consisting of multiple atomic tasks, by deploying robots in dynamic and unpredictable environments such as industrial and agricultural settings. A key characteristic of these contexts is that activities are not predefined: while they involve a limited set of possible tasks, their combinations may vary depending on the situation. Moreover, despite recent advances in robotics, the ability for humans to monitor the progress of high-level activities - in terms of past, present, and future actions - remains fundamental to ensure the correct execution of safety-critical processes. In this paper, we introduce a general architecture that integrates Large Language Models (LLMs) with automated planning, enabling humans to specify high-level activities (also referred to as processes) using natural language, and to monitor their execution by querying a robot. We also present an implementation of this architecture using state-of-the-art components and quantitatively evaluate the approach in a real-world precision agriculture scenario. I. INTRODUCTION In recent years, there has been a significant increase in the interest and demand for automating complex and labor-intensive activities through the deployment of robotic systems. These activities, often encountered in industrial and agricultural domains, are typically composed of multiple, smaller atomic subtasksthat must be coordinated to achieve a larger goal. What makes these environments particularly challenging is their dynamic and unpredictable nature: the specific sequence and combination of tasks required can change based on real-time conditions, external events, or evolving objectives. Importantly, while the range of possible jobs is usually limited and known in advance, the structure and flow of the overall activity are not fixed and therefore must be adapted on the fly. In such contexts, human operators must maintain a clear understanding of ongoing high-level activities, both to ensure correctness and to make timely decisions. This includes being aware of what the system has done (past), what it is currently doing (present), and what it intends to do next (future). However, this kind of situational awareness is difficult to maintain in the absence of mechanisms for querying the system in a human-friendly way.

Belief-Desire-Intention (BDI) is a framework for modelling agents based on their beliefs, desires, and intentions. Plans are a central component of BDI agents, and define sequences of actions that an agent must undertake to achieve a certain goal. Existing approaches to plan generation often require significant manual effort, and are mainly focused on single-agent systems. As a result, in this work, we have developed a tool that automatically generates BDI plans using Alternating-Time Temporal Logic (ATL). By using ATL, the plans generated accommodate for possible competition or cooperation between the agents in the system. We demonstrate the effectiveness of the tool by generating plans for an illustrative game that requires agent collaboration to achieve a shared goal. We show that the generated plans allow the agents to successfully attain this goal.

Online planning in Markov Decision Processes (MDPs) enables agents to make sequential decisions by simulating future trajectories from the current state, making it well-suited for large-scale or dynamic environments. Sample-based methods such as Sparse Sampling and Monte Carlo Tree Search (MCTS) are widely adopted for their ability to approximate optimal actions using a generative model. However, in practical settings, the generative model is often learned from limited data, introducing approximation errors that can degrade performance or lead to unsafe behaviors. To address these challenges, Robust MDPs (RMDPs) offer a principled framework for planning under model uncertainty, yet existing approaches are typically computationally intensive and not suited for real-time use. In this work, we introduce Robust Sparse Sampling (RSS), the first online planning algorithm for RMDPs with finite-sample theoretical performance guarantees. Unlike Sparse Sampling, which estimates the nominal value function, RSS computes a robust value function by leveraging the efficiency and theoretical properties of Sample Average Approximation (SAA), enabling tractable robust policy computation in online settings. RSS is applicable to infinite or continuous state spaces, and its sample and computational complexities are independent of the state space size. We provide theoretical performance guarantees and empirically show that RSS outperforms standard Sparse Sampling in environments with uncertain dynamics.

Multimodal Multi-hop question answering requires integrating information from diverse sources, such as images and texts, to derive answers. Existing methods typically rely on sequential retrieval and reasoning, where each step builds on the previous output. However, this single-path paradigm makes them vulnerable to errors due to misleading intermediate steps. Moreover, developing multimodal models can be computationally expensive, often requiring extensive training. To address these limitations, we propose a training-free framework guided by an Adaptive Planning Graph, which consists of planning, retrieval and reasoning modules. The planning module analyzes the current state of the Adaptive Planning Graph, determines the next action and where to expand the graph, which enables dynamic and flexible exploration of reasoning paths. To handle retrieval of text to unspecified target modalities, we devise modality-specific strategies that dynamically adapt to distinct data types. Our approach preserves the characteristics of multimodal information without costly task-specific training, enabling seamless integration with up-to-date models. Finally, the experiments on MultimodalQA and WebQA show that our approach matches or outperforms existing models that rely on training.

Abstract--Metro crew planning is a key component of smart city development as it directly impacts the operational efficiency and service reliability of public transportation. With the rapid expansion of metro networks, effective multi-line scheduling and emergency management have become essential for large-scale seamless operations. However, current research focuses primarily on individual metro lines, with insufficient attention on cross-line coordination and rapid replanning during disruptions. Here, a unified optimization framework is presented for multi-line metro crew planning and replanning with heterogeneous workforce. Specifically, a hierarchical time-space network model is proposed to represent the unified crew action space, and computationally efficient constraints and formulations are derived for the crew's heterogeneous qualifications and preferences. Solution algorithms based on column generation and shortest path adjustment are further developed, utilizing the proposed network model. Experiments with real data from Shanghai and Beijing Metro demonstrate that the proposed methods outperform benchmark heuristics in both cost reduction and task completion, and achieve notable efficiency gains by incorporating cross-line operations, particularly for urgent tasks during disruptions. This work highlights the role of global optimization and cross-line coordination in multi-line metro system operations, providing insights into the efficient and reliable functioning of public transportation in smart cities. Metro systems are vital to urban transportation, offering high efficiency and large capacity to meet growing mobility demands. Within the context of metro operations, labor costs account for a significant share of expenses [1]. Consequently, metro crew planning plays a crucial factor in achieving smooth, cost-effective operations. As metro systems continue to expand rapidly, the need for optimized crew planning approaches has become increasingly critical to realize efficient and intelligent metro operations that support the broader goals of smart city development [2]. Existing research on metro crew planning primarily focuses on single-line operations [3], [4], [5], [6], [7], [8].

This paper presents a system for autonomous semantic exploration and dense semantic target mapping of a complex unknown environment using a ground robot equipped with a LiDAR-panoramic camera suite. Existing approaches often struggle to balance collecting high-quality observations from multiple view angles and avoiding unnecessary repetitive traversal. To fill this gap, we propose a complete system combining mapping and planning. We first redefine the task as completing both geometric coverage and semantic viewpoint observation. We then manage semantic and geometric viewpoints separately and propose a novel Priority-driven Decoupled Local Sampler to generate local viewpoint sets. This enables explicit multi-view semantic inspection and voxel coverage without unnecessary repetition. Building on this, we develop a hierarchical planner to ensure efficient global coverage. In addition, we propose a Safe Aggressive Exploration State Machine, which allows aggressive exploration behavior while ensuring the robot's safety. Our system includes a plug-and-play semantic target mapping module that integrates seamlessly with state-of-the-art SLAM algorithms for pointcloud-level dense semantic target mapping. We validate our approach through extensive experiments in both realistic simulations and complex real-world environments. Simulation results show that our planner achieves faster exploration and shorter travel distances while guaranteeing a specified number of multi-view inspections. Real-world experiments further confirm the system's effectiveness in achieving accurate dense semantic object mapping of unstructured environments.

We propose a new formulation for the multi-robot task allocation problem that incorporates (a) complex precedence relationships between tasks, (b) efficient intra-task coordination, and (c) cooperation through the formation of robot coalitions. A task graph specifies the tasks and their relationships, and a set of reward functions models the effects of coalition size and preceding task performance. Maximizing task rewards is NP-hard; hence, we propose network flow-based algorithms to approximate solutions efficiently. A novel online algorithm performs iterative re-allocation, providing robustness to task failures and model inaccuracies to achieve higher performance than offline approaches. We comprehensively evaluate the algorithms in a testbed with random missions and reward functions and compare them to a mixed-integer solver and a greedy heuristic. Additionally, we validate the overall approach in an advanced simulator, modeling reward functions based on realistic physical phenomena and executing the tasks with realistic robot dynamics. Results establish efficacy in modeling complex missions and efficiency in generating high-fidelity task plans while leveraging task relationships.

This study presents a system integration approach for planning schedules, sequences, tasks, and motions for reconfigurable robots to automatically disassemble constrained structures in a non-destructive manner. Such systems must adapt their configuration and coordination to the target structure, but the large and complex search space makes them prone to local optima. To address this, we integrate multiple robot arms equipped with different types of tools, together with a rotary stage, into a reconfigurable setup. This flexible system is based on a hierarchical optimization method that generates plans meeting multiple preferred conditions under mandatory requirements within a realistic timeframe. The approach employs two many-objective genetic algorithms for sequence and task planning with motion evaluations, followed by constraint programming for scheduling. Because sequence planning has a much larger search space, we introduce a chromosome initialization method tailored to constrained structures to mitigate the risk of local optima. Simulation results demonstrate that the proposed method effectively solves complex problems in reconfigurable robotic disassembly.

Application migration in edge-cloud system enables high QoS and cost effective service delivery. However, automatically orchestrating such migration is typically solved with heuristic approaches. Starting from the Markov Decision Process (MDP), in this paper, we identify, analyze and compare selected state-of-the-art Artificial Intelligence (AI) planning and Reinforcement Learning (RL) approaches for solving the class of edge-cloud application migration problems that can be modeled as Towers of Hanoi (ToH) problems. We introduce a new classification based on state space definition and analyze the compared models also through this lense. The aim is to understand available techniques capable of orchestrating such application migration in emerging computing continuum environments.

Large language models (LLMs) have demonstrated impressive capabilities across diverse tasks, yet their ability to perform structured symbolic planning remains limited, particularly in domains requiring formal representations like the Planning Domain Definition Language (PDDL). In this paper, we present a novel instruction tuning framework, PDDL-Instruct, designed to enhance LLMs' symbolic planning capabilities through logical chain-of-thought reasoning. Our approach focuses on teaching models to rigorously reason about action applicability, state transitions, and plan validity using explicit logical inference steps. By developing instruction prompts that guide models through the precise logical reasoning required to determine when actions can be applied in a given state, we enable LLMs to self-correct their planning processes through structured reflection. The framework systematically builds verification skills by decomposing the planning process into explicit reasoning chains about precondition satisfaction, effect application, and invariant preservation. Experimental results on multiple planning domains show that our chain-of-thought reasoning based instruction-tuned models are significantly better at planning, achieving planning accuracy of up to 94% on standard benchmarks, representing a 66% absolute improvement over baseline models. This work bridges the gap between the general reasoning capabilities of LLMs and the logical precision required for automated planning, offering a promising direction for developing better AI planning systems.