Systems & Control

Lujie Yang, Hongkai Dai, Zhouxing Shi et al. · mit

This work addresses the problem of ensuring stability in learning-based control for robotics and control applications, offering a more efficient and flexible solution compared to existing methods.

Kaizhen Zhu, Mokai Pan, Yuexin Ma et al.

This work addresses the problem of image detail preservation in diffusion bridge models for computer vision researchers and practitioners, providing an incremental yet significant improvement over existing approaches.

Manish Prajapat, Johannes Köhler, Melanie N. Zeilinger et al.

This addresses the critical safety challenge for real-world deployment of agents like autonomous cars and drones in non-episodic settings, representing a novel foundational advance rather than an incremental improvement.

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang et al.

This addresses a common problem in RL for applications with delayed sensory perceptions, offering a novel solution that outperforms state-of-the-art methods.

Tairan He, Zhengyi Luo, Wenli Xiao et al. · cmu

This enables real-time humanoid robot control for applications like remote operations or human-robot interaction, representing a novel demonstration in learning-based teleoperation.

Haoran Li, Muhao Guo, Marija Ilic et al.

This addresses the challenge of integrating heterogeneous external factors for power system reliability, representing a novel paradigm shift rather than an incremental improvement.

Shida Jiang, Junzhe Shi, Scott Moura

This addresses a foundational issue in state estimation for nonlinear systems, which is critical for applications like robotics and control, though it is incremental as it builds on existing nonlinear Kalman filter methods.

Hans van Gorp, Davide Belli, Amir Jalalirad et al.

This work addresses improved positioning accuracy for GNSS users in challenging urban scenarios, representing a novel deep learning-based integration approach.

Andrea Bajcsy, Jaime F. Fisac

This work addresses safety concerns for advanced AI technologies interacting with humans, presenting a novel interdisciplinary approach that is foundational rather than incremental.

Luca Benfenati, Daniele Jahier Pagliari, Luca Zanatta et al.

This addresses safety and reliability issues in civil infrastructure monitoring, offering a novel approach with significant performance gains over traditional methods.

Jeffrey Fang, Glen Chou

This addresses the problem of real-time safe control for high-dimensional uncertain robotic systems, offering a significant performance improvement over existing methods.

Tairan He, Chong Zhang, Wenli Xiao et al.

This addresses the challenge for legged robotics of balancing agility and safety in real-world navigation, representing a novel integration rather than an incremental improvement.

Haoyu Li, Xiangru Zhong, Bin Hu et al.

This work addresses the problem of ensuring stability in neural controllers for nonlinear systems, which is critical for safety-critical applications like robotics and autonomous systems, representing a significant advance over prior methods.

Stefan Podgorski, Sourav Garg, Mehdi Hosseinzadeh et al.

This addresses the problem of computationally expensive and non-generalizable navigation for robotics in open-set environments, offering a more robust solution.

Petar Bevanda, Max Beier, Armin Lederer et al.

This work addresses the problem of reliable decision-making in dynamical systems, which is crucial for various fields that rely on forecasting and representation learning, such as control systems or time-series analysis, with an incremental approach.

Zhao-Heng Yin, Changhao Wang, Luis Pineda et al. · cmu, meta-ai

It addresses the problem of robot dexterity for robotics, offering a novel hybrid approach rather than an incremental improvement.

Xingang Guo, Darioush Keivan, Usman Syed et al.

This addresses the challenge of applying LLMs to complex control theory tasks in sectors like aerospace and robotics, offering a fully automated alternative to human-involved design processes.

Grigory Neustroev, Mirco Giacobbe, Anna Lukina

This work addresses the need for continuous-time reasoning in autonomous learning systems, bridging a gap between existing discrete-time methods and deterministic continuous-time approaches.

Manish Prajapat, Johannes Köhler, Matteo Turchetta et al.

This addresses a fundamental problem in robotics for autonomous task completion, offering a first-of-its-kind solution with broad applicability to real-world scenarios with complex non-linear dynamics.

Reda El Makroum, Sebastian Zwickl-Bernhard, Lukas Kranzl

This addresses user interaction barriers in home energy management for residential electricity consumers, representing a novel application rather than an incremental improvement.