中文
相关论文

相关论文: End-to-end Learning of Driving Models from Large-s…

200 篇论文

In this paper we present a complete study of an end-to-end imitation learning system for speed control of a real car, based on a neural network with a Long Short Term Memory (LSTM). To achieve robustness and generalization from expert…

计算机视觉与模式识别 · 计算机科学 2018-12-17 Laurent George , Thibault Buhet , Emilie Wirbel , Gaetan Le-Gall , Xavier Perrotton

Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In…

机器学习 · 计算机科学 2016-04-20 Sergey Levine , Chelsea Finn , Trevor Darrell , Pieter Abbeel

Traditional autonomous driving methods adopt a modular design, decomposing tasks into sub-tasks. In contrast, end-to-end autonomous driving directly outputs actions from raw sensor data, avoiding error accumulation. However, training an…

机器人学 · 计算机科学 2024-11-22 Zeyu Dong , Yimin Zhu , Yansong Li , Kevin Mahon , Yu Sun

Most self-driving systems rely on hand-coded perception outputs and engineered driving rules. Learning directly from human driving data with an end-to-end method can allow for a training architecture that is simpler and scales well with…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Mitchell Goff , Greg Hogan , George Hotz , Armand du Parc Locmaria , Kacper Raczy , Harald Schäfer , Adeeb Shihadeh , Weixing Zhang , Yassine Yousfi

Anticipating the motion of neighboring vehicles is crucial for autonomous driving, especially on congested highways where even slight motion variations can result in catastrophic collisions. An accurate prediction of a future trajectory…

计算机视觉与模式识别 · 计算机科学 2023-04-20 Fuad Hasan , Hailong Huang

In recent years, considerable progress has been made towards a vehicle's ability to operate autonomously. An end-to-end approach attempts to achieve autonomous driving using a single, comprehensive software component. Recent breakthroughs…

机器人学 · 计算机科学 2019-05-17 Hege Haavaldsen , Max Aasboe , Frank Lindseth

Current autonomous driving systems are composed of a perception system and a decision system. Both of them are divided into multiple subsystems built up with lots of human heuristics. An end-to-end approach might clean up the system and…

计算机视觉与模式识别 · 计算机科学 2020-10-12 Jianyu Chen , Zhuo Xu , Masayoshi Tomizuka

In this paper, we develop deep spatio-temporal neural networks to sequentially count vehicles from low quality videos captured by city cameras (citycams). Citycam videos have low resolution, low frame rate, high occlusion and large…

计算机视觉与模式识别 · 计算机科学 2017-08-02 Shanghang Zhang , Guanhang Wu , João P. Costeira , José M. F. Moura

Steering a car through traffic is a complex task that is difficult to cast into algorithms. Therefore, researchers turn to training artificial neural networks from front-facing camera data stream along with the associated steering angles.…

机器学习 · 计算机科学 2017-11-23 Hesham M. Eraqi , Mohamed N. Moustafa , Jens Honer

In this work, we study vision-based end-to-end reinforcement learning on vehicle control problems, such as lane following and collision avoidance. Our controller policy is able to control a small-scale robot to follow the right-hand lane of…

机器学习 · 计算机科学 2020-12-15 András Kalapos , Csaba Gór , Róbert Moni , István Harmati

Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate…

机器人学 · 计算机科学 2018-03-05 Felipe Codevilla , Matthias Müller , Antonio López , Vladlen Koltun , Alexey Dosovitskiy

Tactical decision making and strategic motion planning for autonomous highway driving are challenging due to the complication of predicting other road users' behaviors, diversity of environments, and complexity of the traffic interactions.…

机器人学 · 计算机科学 2020-11-30 Majid Moghadam , Ali Alizadeh , Engin Tekin , Gabriel Hugh Elkaim

End-to-end learning directly maps sensory inputs to actions, creating highly integrated and efficient policies for complex robotics tasks. However, such models often struggle to generalize beyond their training scenarios, limiting…

机器人学 · 计算机科学 2025-05-19 Makram Chahine , Alex Quach , Alaa Maalouf , Tsun-Hsuan Wang , Daniela Rus

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for…

计算机视觉与模式识别 · 计算机科学 2019-09-17 Seokju Lee , Junsik Kim , Tae-Hyun Oh , Yongseop Jeong , Donggeun Yoo , Stephen Lin , In So Kweon

Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize at scale. However,…

机器人学 · 计算机科学 2020-07-08 Jianyu Chen , Shengbo Eben Li , Masayoshi Tomizuka

We study active object tracking, where a tracker takes visual observations (i.e., frame sequences) as input and produces the corresponding camera control signals as output (e.g., move forward, turn left, etc.). Conventional methods tackle…

计算机视觉与模式识别 · 计算机科学 2019-02-14 Wenhan Luo , Peng Sun , Fangwei Zhong , Wei Liu , Tong Zhang , Yizhou Wang

It is doubtful that animals have perfect inverse models of their limbs (e.g., what muscle contraction must be applied to every joint to reach a particular location in space). However, in robot control, moving an arm's end-effector to a…

机器人学 · 计算机科学 2022-09-19 Justus Huebotter , Serge Thill , Marcel van Gerven , Pablo Lanillos

Learning from demonstration for motion planning is an ongoing research topic. In this paper we present a model that is able to learn the complex mapping from raw 2D-laser range findings and a target position to the required steering…

机器人学 · 计算机科学 2018-11-07 Mark Pfeiffer , Michael Schaeuble , Juan Nieto , Roland Siegwart , Cesar Cadena

In this work we explore the advantages of end-to-end learning of multilayer maps offered by feed forward neural-networks (FFNN) for learning and predicting dynamics from transient fluid flow data.While machine learning in general depends on…

计算物理 · 物理学 2020-10-28 Shivakanth Chary Puligilla , Balaji Jayaraman

Motion Planning, as a fundamental technology of automatic navigation for the autonomous vehicle, is still an open challenging issue in the real-life traffic situation and is mostly applied by the model-based approaches. However, due to the…

计算机视觉与模式识别 · 计算机科学 2019-03-06 Zhengwei Bai , Baigen Cai , Wei Shangguan , Linguo Chai
‹ 上一页 1 2 3 10 下一页 ›