27 papers · ranked by Valyu relevance
Suraj Borate, Bhavish Rai B, Vipul Pardeshi, Madhu Vadali
Heterogeneous multi-robot teams require systems that can interpret natural-language goals, allocate tasks, and adapt to unexpected events. We developed CoMuRoS (Collaborative Multi-Robot System), a generalizable hierarchical architecture combining a centralized task-manager LLM with decentralized robot-level LLMs for…
Carlos G. Correa, Mark K. Ho, Frederick Callaway, Nathaniel D. Daw + 2 more
'Thomas L. Griffiths' 'Tobias U. Hauser'] Human behavior emerges from planning over elaborate decompositions of tasks into goals, subgoals, and low-level actions. How are these decompositions created and used? Here, we propose and evaluate a normative framework for task decomposition based on the simple idea that…
Yunfan Li, Bingbing Xu, Xueyun Tian, Xiucheng Xu + 1 more
Recent advances in large language models (LLMs) have enabled agents to autonomously execute complex, long-horizon tasks, yet planning remains a primary bottleneck for reliable task execution. Existing methods typically fall into two paradigms: step-wise planning, which is reactive but often short-sighted; and one-shot…
Samuele Sandrini, Marco Faroni, Nicola Pedrocchi
—A good estimation of the actions' cost is key in task planning for human-robot collaboration. The duration of an action depends on agents' capabilities and the correlation between actions performed simultaneously by the human and the robot. This paper proposes an approach to learning actions' costs and coupling…
Yuliang Li, Nitin Kamra, Ruta Desai, Alon Halevy
LLMs have recently made impressive inroads on tasks whose output is structured, such as coding, robotic planning and querying databases. The vision of creating AI-powered personal assistants also involves creating structured outputs, such as a plan for one's day, or for an overseas trip. Here, since the plan is…
Afagh Mehri Shervedani, Matthew R. Walter, Milos Zefran
— Recent advances in large language models (LLMs) have demonstrated their potential as planners in human-robot collaboration (HRC) scenarios, offering a promising alternative to traditional planning methods. LLMs, which can generate structured plans by reasoning over natural language inputs, have the ability to…
Raquel Fuentetaja, Angel García-Olaya, Javier García, José Carlos González + 1 more
'José Carlos González' 'Fernando Fernández'] Using Automated Planning for the high level control of robotic architectures is becoming very popular thanks mainly to its capability to define the tasks to perform in a declarative way. However, classical planning tasks, even in its basic standard Planning Domain Definition…
Marco Aiello, Ilche Georgievski
These are notes for lectures presented at the University of Stuttgart that provide an introduction to key concepts and techniques in AI Planning. Artificial Intelligence Planning, also known as Automated Planning, emerged somewhere in 1966 from the need to give autonomy to a wheeled robot. Since then, it has evolved…
Rebecca Eifler, Jörg Hoffmann
In a variety of application settings, the user preference for a planning task – the precise optimization objective – is difficult to elicit. One possible remedy is planning as an iterative process, allowing the user to iteratively refine and modify example plans. A key step to support such a process are explanations…
Yuxuan Li, James L. McClelland
When we choose actions aimed at achieving long-range goals, proximal information cannot be exploited in a blindly myopic way, as relevant future information must often be taken into account. However, when long-range information is irrelevant to achieving proximal subgoals, it can be desirable to focus exclusively on…
Maoxin Zhang, Björn Andersson, Samuel Greiff
Problem-solving is a critical aspect of intelligence that has become increasingly important in modern society. Mapping out the determinants of success in problem-solving helps understand the underlying cognitive processes involved. This article focuses on two key cognitive processes in problem-solving: non-targeted…
Fatmaalzahraa A Aboalasaad, Leonie Lambertz, Chiara Mastrogiuseppe, Rubén Moreno-Bote
In our everyday lives, we continually need to commit to courses of future action even when direct feedback is not available. The expected reward of an action depends not only on a single decision but on a sequence of interdependent choices that will happen in the future. Admittedly, most decisions we make concern…
Moritz J. F. Krusche, Eric Schulz, Arthur Guez, Maarten Speekenbrink
How do people plan ahead when searching for rewards? We investigate planning in a foraging task in which participants search for rewards on an infinite two-dimensional grid. Our results show that their search is best-described by a model which searches approximately 3 steps ahead. Furthermore, participants do not seem…
Momchil S. Tomov, Samyukta Yagati, Agni Kumar, Wanqian Yang + 1 more
We propose that humans spontaneously organize environments into clusters of states that support hierarchical planning, enabling them to tackle challenging problems by breaking them down into sub-problems at various levels of abstraction. People constantly rely on such hierarchical presentations to accomplish tasks big…
Helen Harman, Keshav Chintamani, Pieter Simoens
By coupling a robot to a smart environment, the robot can sense state beyond the perception range of its onboard sensors and gain greater actuation capabilities. Nevertheless, incorporating the states and actions of Internet of Things (IoT) devices into the robot’s onboard planner increases the computational load, and…
Valeria Simonelli, Davide Nuzzi, Gian Luca Lancia, Giovanni Pezzulo
Shortest Path Planning Authors: ['Valeria Simonelli' 'Davide Nuzzi' 'Gian Luca Lancia' 'Giovanni Pezzulo'] Effective planning is crucial for navigating complex environments and achieving goals efficiently. In this study, we investigated how environmental structure influences the selection of planning strategies.…
Mattia Eluchans, Gian Luca Lancia, Antonella Maselli, Marco D’Alessando + 2 more
We humans are capable of solving challenging planning problems, but the range of adaptive strategies that we use to address them are not yet fully characterized. Here, we designed a series of problem-solving tasks that require planning at different depths. After systematically comparing the performance of participants…
Authors not listed
Agentic artificial intelligence (AI) is poised to redefine how science is conducted, automating not just data analysis but the entire research lifecycle, from hypothesis generation to validation. Yet most current AI agents remain domain-bound, tailored to specific applications such as materials synthesis or quantum…
Zhaojun Li, Paul De Boeck, Jian Li, Alexander Volfovsky
Planning and execution are two important parts of the problem-solving process. Based on related research, it is expected that planning speed and execution speed are positively correlated because of underlying individual differences in general mental speed. While there could also be a direct negative dependency of…
Carlos A. Velázquez-Vargas, Jordan A. Taylor
Many skills that humans acquire throughout their lives, such as playing video games or sports, require substantial motor learning and multi-step planning. While both processes are typically studied separately, they are likely to interact during the acquisition of complex motor skills. In this work, we studied this…
Authors not listed
Automated chemistry platforms hold the potential to enable large-scale organic synthesis campaigns, such as producing a library of compounds for biological evaluation. The efficiency of such platforms will depend on the schedule according to which the synthesis operations are executed. In this work, we study the…
Authors not listed
Computer-aided synthesis planning aims to identify viable synthetic routes from a target compound to readily available building blocks by iteratively decomposing molecules into smaller precursors. Self-play search algorithms, trained with simulated experience, reach state-of-the-art performance. However, these methods…
Elina Renko, Katri Kostamo, Nelli Hankonen
Interestingly, the reasons given for both planning and not planning emphasized the feelings that planning may result in. These feelings reflect the basic psychological needs of autonomy and competence that SDT highlights (Ryan & Deci, ). SDT suggest that nurturing the needs of autonomy, competence and relatedness…
Alan Lindsay, Andrés A. Ramírez-Duque, Bart Craenen, David A. Robb + 4 more
The task of supporting a human operator to understand generated plans, and to explore the plan space, are important problems in automated planning. In this work, we consider the problem of plan explainability and plan space exploration in underwater autonomous vehicle missions. In this context, concepts that are useful…
Authors not listed
We present RetroSynFormer, a novel approach to multi-step retrosynthesis planning. Here, we express the task of iteratively breaking down a compound into building blocks as a sequence-modeling problem and train a model based on the Decision Transformer. The synthesis routes are generated by iteratively predicting…
Grzegorz Skoraczyński, Mateusz Kitlas, Błażej Miasojedow, Anna Gambin
Modern computer-assisted synthesis planning tools provide strong support for this problem. However, they are still limited by computational complexity. This limitation may be overcome by scoring the synthetic accessibility as a pre-retrosynthesis heuristic. A wide range of machine learning scoring approaches is…
Ewa Wieczorek, Joshua W. Sin, Matthew T. O. Holland, Liam Wilbraham + 5 more
Heterocycles are important scaffolds in medicinal chemistry that can be used to modulate the binding mode as well as pharmacokinetic properties of drugs. The importance of heterocycles has been exemplified by the publication of numerous datasets containing heterocyclic rings and their properties. However, those…