Related papers: Temporally Layered Architecture for Adaptive, Dist…
Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering…
A long-standing proposition is that by emulating the operation of the brain's neocortex, a spiking neural network (SNN) can achieve similar desirable features: flexible learning, speed, and efficiency. Temporal neural networks (TNNs) are…
We present a new approach for the design of a synthetic biological circuit whose behaviour is specified in terms of signal temporal logic (STL) formulae. We first show how to characterise with STL formulae the input/output behaviour of…
In this paper, we present Stratified Topological Autonomy for Long-Range Coordination (STALC), a hierarchical planning approach for multi-robot coordination in real-world environments with significant inter-robot spatial and temporal…
Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory tracking performance, provided that any uncertain dynamics…
We propose a Reinforcement Learning (RL) based control design framework for handling complex tasks. The approach extends the concept of Reward Machines (RM) with Signal Temporal Logic (STL) formulas that can be used for event generation.…
Alloy and TLA+ are two formal specification languages that are increasingly popular due to their simplicity and flexibility, as well as the effectiveness of their companion model checkers, the Alloy Analyzer and TLC, respectively.…
Signal Temporal Logic (STL) is a formal language over continuous-time signals (such as trajectories of a multi-agent system) that allows for the specification of complex spatial and temporal system requirements (such as staying sufficiently…
Reinforcement learning (RL) is a promising approach. However, success is limited to real-world applications, because ensuring safe exploration and facilitating adequate exploitation is a challenge for controlling robotic systems with…
Real-world data distributions are often highly skewed. This has spurred a growing body of research on long-tailed recognition, aimed at addressing the imbalance in training classification models. Among the methods studied, multiplicative…
Planning-based reinforcement learning has shown strong performance in tasks in discrete and low-dimensional continuous action spaces. However, planning usually brings significant computational overhead for decision-making, and scaling such…
Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity.…
Recent research has challenged the necessity of complex deep learning architectures for time series forecasting, demonstrating that simple linear models can often outperform sophisticated approaches. Building upon this insight, we introduce…
Effective human-robot collaboration (HRC) requires translating high-level intent into contact-stable whole-body motion while continuously adapting to a human partner. Many vision-language-action (VLA) systems learn end-to-end mappings from…
This letter proposes a three-tier computational architecture for the real-time control of nonlinear complex systems, such as time-dependent PDEs. There is an important class of such problems for which existing single- and two-time-scale…
Embodied task planning requires agents to produce executable actions in a close-loop manner within the environment. With progressively improving capabilities of LLMs in task decomposition, planning, and generalization, current embodied task…
Distributed control algorithms are known to reduce overall computation time compared to centralized control algorithms. However, they can result in inconsistent solutions leading to the violation of safety-critical constraints. Inconsistent…
We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some…
Learning to perform perfect tracking tasks based on measurement data is desirable in the controller design of systems operating repetitively. This motivates the present paper to seek an optimization-based design approach for iterative…
In this paper we present a layered approach for multi-agent control problem, decomposed into three stages, each building upon the results of the previous one. First, a high-level plan for a coarse abstraction of the system is computed,…