We introduce Lazy-DaSH, an improvement over the recent state of the art multi-robot task and motion planning method DaSH, which scales to more than double the number of robots and objects compared to the original method and achieves an order of magnitude faster planning time when applied to a multi-manipulator object rearrangement problem. We achieve this improvement through a hierarchical approach, where a high-level task planning layer identifies planning spaces required for task completion, and motion feasibility is validated lazily only within these spaces. In contrast, DaSH precomputes the motion feasibility of all possible actions, resulting in higher costs for constructing state space representations. Lazy-DaSH maintains efficient query performance by utilizing a constraint feedback mechanism within its hierarchical structure, ensuring that motion feasibility is effectively conveyed to the query process. By maintaining smaller state space representations, our method significantly reduces both representation construction time and query time. We evaluate Lazy-DaSH in four distinct scenarios, demonstrating its scalability to increasing numbers of robots and objects, as well as its adaptability in resolving conflicts through the constraint feedback mechanism.

As an important branch of embodied artificial intelligence, mobile manipulators are increasingly applied in intelligent services, but their redundant degrees of freedom also limit efficient motion planning in cluttered environments. To address this issue, this paper proposes a hybrid learning and optimization framework for reactive whole-body motion planning of mobile manipulators. We develop the Bayesian distributional soft actor-critic (Bayes-DSAC) algorithm to improve the quality of value estimation and the convergence performance of the learning. Additionally, we introduce a quadratic programming method constrained by the signed distance field to enhance the safety of the obstacle avoidance motion. We conduct experiments and make comparison with standard benchmark. The experimental results verify that our proposed framework significantly improves the efficiency of reactive whole-body motion planning, reduces the planning time, and improves the success rate of motion planning. Additionally, the proposed reinforcement learning method ensures a rapid learning process in the whole-body planning task. The novel framework allows mobile manipulators to adapt to complex environments more safely and efficiently.

This paper focuses on the need for a rigorous theory of layered control architectures (LCAs) for complex engineered and natural systems, such as power systems, communication networks, autonomous robotics, bacteria, and human sensorimotor control. All deliver extraordinary capabilities, but they lack a coherent theory of analysis and design, partly due to the diverse domains across which LCAs can be found. In contrast, there is a core universal set of control concepts and theory that applies very broadly and accommodates necessary domain-specific specializations. However, control methods are typically used only to design algorithms in components within a larger system designed by others, typically with minimal or no theory. This points towards a need for natural but large extensions of robust performance from control to the full decision and control stack. It is encouraging that the successes of extant architectures from bacteria to the Internet are due to strikingly universal mechanisms and design patterns. This is largely due to convergent evolution by natural selection and not intelligent design, particularly when compared with the sophisticated design of components. Our aim here is to describe the universals of architecture and sketch tentative paths towards a useful design theory.

The usage of Large Language Models (LLMs) has increased recently, not only due to the significant improvements in their accuracy but also because of the use of the quantization that allows running these models without intense hardware requirements. As a result, the LLMs have proliferated. It implies the creation of a great variety of LLMs with different capabilities. This way, this paper proposes the integration of LLMs in cognitive architectures for autonomous robots. Specifically, we present the design, development and deployment of the llama\_ros tool that allows the easy use and integration of LLMs in ROS 2-based environments, afterward integrated with the state-of-the-art cognitive architecture MERLIN2 for updating a PDDL-based planner system. This proposal is evaluated quantitatively and qualitatively, measuring the impact of incorporating the LLMs in the cognitive architecture.

As the number of Human-Centered Internet of Things (HCIoT) applications increases, the self-adaptation of its services and devices is becoming a fundamental requirement for addressing the uncertainties of the environment in decision-making processes. Self-adaptation of HCIoT aims to manage run-time changes in a dynamic environment and to adjust the functionality of IoT objects in order to achieve desired goals during execution. SMASH is a semantic-enabled multi-agent system for self-adaptation of HCIoT that autonomously adapts IoT objects to uncertainties of their environment. SMASH addresses the self-adaptation of IoT applications only according to the human values of users, while the behavior of users is not addressed. This article presents Q-SMASH: a multi-agent reinforcement learning-based approach for self-adaptation of IoT objects in human-centered environments. Q-SMASH aims to learn the behaviors of users along with respecting human values. The learning ability of Q-SMASH allows it to adapt itself to the behavioral change of users and make more accurate decisions in different states and situations.

Solving long-horizon sequential decision making tasks in environments with sparse rewards is a longstanding problem in reinforcement learning (RL) research. Hierarchical Reinforcement Learning (HRL) has held the promise to enhance the capabilities of RL agents via operation on different levels of temporal abstraction. Despite the success of recent works in dealing with inherent nonstationarity and sample complexity, it remains difficult to generalize to unseen environments and to transfer different layers of the policy to other agents. In this paper, we propose a novel HRL architecture, Hierarchical Decompositional Reinforcement Learning (HiDe), which allows decomposition of the hierarchical layers into independent subtasks, yet allows for joint training of all layers in end-to-end manner. The main insight is to combine a control policy on a lower level with an image-based planning policy on a higher level. We evaluate our method on various complex continuous control tasks, demonstrating that generalization across environments and transfer of higher level policies, such as from a simple ball to a complex humanoid, can be achieved. See videos https://sites.google.com/view/hide-rl.