Related papers: Implicit Action Chunking for Smooth Continuous Con…

While reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critical systems. In this work, we address this issue by a safety…

Fully supervised action segmentation works on frame-wise action recognition with dense annotations and often suffers from the over-segmentation issue. Existing works have proposed a variety of solutions such as boundary-aware networks,…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

A key limitation in using various modern methods of machine learning in developing feedback control policies is the lack of appropriate methodologies to analyze their long-term dynamics, in terms of making any sort of guarantees (even…

In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon tasks. However, DT's performance depends heavily on the coverage of collected…

Tasks involving high-risk-high-return (HRHR) actions, such as obstacle crossing, often exhibit multimodal action distributions and stochastic returns. Most reinforcement learning (RL) methods assume unimodal Gaussian policies and rely on…

Reinforcement learning is applied to the development of control strategies in order to reduce skin friction drag in a fully developed turbulent channel flow at a low Reynolds number. Motivated by the so-called opposition control (Choi et…

Opening heavy, self closing doors, especially those that require pulling remains a long standing challenge in robotics. Humans naturally employ both arms in a dexterous manner, rotating the handle, widening the gap, holding the door,…

Dynamic motions are a key feature of robotic arms, enabling them to perform tasks quickly and efficiently. Soft continuum manipulators do not currently consider dynamic parameters when operating in task space. This shortcoming makes…

Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or collisions. Backdoor functionality is typically incorporated…

Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are a key enabler for objective-driven self-adaptation under…

Diffusing wave spectroscopy (DWS) is a well-known set of methods to measure the temporal dynamics of dynamic samples. In DWS, dynamic samples scatter the incident coherent light, and the information of the temporal dynamics is encoded in…

Tactical driving decision making is crucial for autonomous driving systems and has attracted considerable interest in recent years. In this paper, we propose several practical components that can speed up deep reinforcement learning…

This paper addresses the problem of safe optimization under a single smooth constraint, a scenario that arises in diverse real-world applications such as robotics and autonomous navigation. The objective of safe optimization is to solve a…

This paper proposes a novel technique called "successive stochastic smoothing" that optimizes nonsmooth and discontinuous functions while considering various constraints. Our methodology enables local and global optimization, making it a…

Emerging networked systems such as industrial IoT and real-time cyber-physical infrastructures demand intelligent scheduling strategies capable of adapting to dynamic traffic, deadlines, and interference constraints. In this work, we…

This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the…

Robotic grasping under uncertainty remains a fundamental challenge due to its uncertain and contact-rich nature. Traditional rigid robotic hands, with limited degrees of freedom and compliance, rely on complex model-based and heavy feedback…

We present a new class of structured reinforcement learning policy-architectures, Implicit Two-Tower (ITT) policies, where the actions are chosen based on the attention scores of their learnable latent representations with those of the…

Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently continuous representations struggle to capture discontinuities and sharp transitions. Existing…