English
Related papers

Related papers: Differentiable Forward Kinematics for TensorFlow 2

200 papers

Tensor Train decomposition is used across many branches of machine learning. We present T3F -- a library for Tensor Train decomposition based on TensorFlow. T3F supports GPU execution, batch processing, automatic differentiation, and…

Mathematical Software · Computer Science 2020-03-04 Alexander Novikov , Pavel Izmailov , Valentin Khrulkov , Michael Figurnov , Ivan Oseledets

This paper presents tensorflow-riemopt, a Python library for geometric machine learning in TensorFlow. The library provides efficient implementations of neural network layers with manifold-constrained parameters, geometric operations on…

Mathematical Software · Computer Science 2025-12-18 Oleg Smirnov

In the field of machine learning, comprehending the intricate training dynamics of neural networks poses a significant challenge. This paper explores the training dynamics of neural networks, particularly whether these dynamics can be…

Machine Learning · Computer Science 2024-08-16 Yeachan Park

Ensuring safety and robustness of robot skills is becoming crucial as robots are required to perform increasingly complex and dynamic tasks. The former is essential when performing tasks in cluttered environments, while the latter is…

Robotics · Computer Science 2025-04-29 Ken-Joel Simmoteit , Philipp Schillinger , Leonel Rozo

The current dominant paradigm for robotic manipulation involves two separate stages: manipulator design and control. Because the robot's morphology and how it can be controlled are intimately linked, joint optimization of design and control…

Robotics · Computer Science 2021-08-25 Jie Xu , Tao Chen , Lara Zlokapa , Michael Foshey , Wojciech Matusik , Shinjiro Sueda , Pulkit Agrawal

Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide. In this work, we propose to tackle this issue by employing a deep neural network with a modular…

Robotics · Computer Science 2019-03-12 Aleksi Hämäläinen , Karol Arndt , Ali Ghadirzadeh , Ville Kyrki

Today, artificial neural networks are one of the major innovators pushing the progress of machine learning. This has particularly affected the development of neural network accelerating hardware. However, since most of these architectures…

Hardware Architecture · Computer Science 2021-02-12 Simon Pfenning , Philipp Holzinger , Marc Reichenbach

Predicting the motion of a mobile agent from a third-person perspective is an important component for many robotics applications, such as autonomous navigation and tracking. With accurate motion prediction of other agents, robots can plan…

Robotics · Computer Science 2018-10-18 Yanfu Zhang , Wenshan Wang , Rogerio Bonatti , Daniel Maturana , Sebastian Scherer

Differentiable simulation enables gradients to be back-propagated through physics simulations. In this way, one can learn the dynamics and properties of a physics system by gradient-based optimization or embed the whole differentiable…

Machine Learning · Computer Science 2023-05-02 Yaofeng Desmond Zhong , Jiequn Han , Biswadip Dey , Georgia Olympia Brikis

Fast and precise motion control is important for industrial robots in manufacturing applications. However, some collaborative robots sacrifice precision for safety, particular for high motion speed. The performance degradation is caused by…

Robotics · Computer Science 2019-08-12 Shuyang Chen , John T. Wen

Self-driving vehicles (SDVs) hold great potential for improving traffic safety and are poised to positively affect the quality of life of millions of people. To unlock this potential one of the critical aspects of the autonomous technology…

Traditional software development in robotics is about programming functionality in the CPU of a given robot with a pre-defined architecture and constraints. With adaptive computing, instead, building a robotic behavior is about programming…

Robotics · Computer Science 2021-09-09 Víctor Mayoral-Vilches , Giulio Corradi

Visual servoing enables robotic systems to perform accurate closed-loop control, which is required in many applications. However, existing methods either require precise calibration of the robot kinematic model and cameras or use neural…

A method to increase the precision of feedforward networks is proposed. It requires a prior knowledge of a target function derivatives of several orders and uses this information in gradient based training. Forward pass calculates not only…

Neural and Evolutionary Computing · Computer Science 2020-04-08 V. I. Avrutskiy

The sample inefficiency of reinforcement learning (RL) remains a significant challenge in robotics. RL requires large-scale simulation and can still cause long training times, slowing research and innovation. This issue is particularly…

Robotics · Computer Science 2026-01-16 Johannes Heeg , Yunlong Song , Davide Scaramuzza

Differentiable simulation establishes the mathematical foundation for solving challenging inverse problems in computer graphics and robotics, such as physical system identification and inverse dynamics control. However, rigor in frictional…

Graphics · Computer Science 2026-05-19 Ziqiu Zeng , Gang Yang , Zhenhao Huang , Bingyang Zhou , Yulin Li , Jason Pho , Siyuan Luo , Fan Shi

Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer from heavy reward engineering, high variance, and slow…

Computer Vision and Pattern Recognition · Computer Science 2023-04-27 Jiawei Ren , Cunjun Yu , Siwei Chen , Xiao Ma , Liang Pan , Ziwei Liu

In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as…

Simulating spatiotemporal turbulence with high fidelity remains a cornerstone challenge in computational fluid dynamics (CFD) due to its intricate multiscale nature and prohibitive computational demands. Traditional approaches typically…

Fluid Dynamics · Physics 2024-07-01 Xiantao Fan , Deepak Akhare , Jian-Xun Wang

Decision-focused learning (DFL) has emerged as a powerful end-to-end alternative to conventional predict-then-optimize (PTO) pipelines by directly optimizing predictive models through downstream decision losses. Existing DFL frameworks are…

Machine Learning · Computer Science 2025-12-01 Xinyu Wang , Jinxiao Du , Yiyang Peng , Wei Ma