相关实验视频

Updated: Jun 16, 2025

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

拉特普:以LiDAR为辅助的多式联运令牌修剪,用于高效地预测自动驾驶的轨迹

Yantao Lu¹, Shiqi Sun¹, Ning Liu²

¹Northwestern Polytechnical University, Xi'an, China.

Neural networks : the official journal of the International Neural Network Society

|June 13, 2025

概括

我们介绍了LiDAR辅助的Token Prune (LaTP),这是一个用于自动驾驶中的大型视觉语言模型 (LVLMs) 的新方法. 通过使用LiDAR数据智能修剪视觉令牌,LaTP提高了轨迹预测效率,大大降低了计算负载而不会牺牲准确度.

科学领域:

计算机视觉计算机视觉
人工智能的人工智能
机器人技术机器人技术机器人技术

背景情况:

大视觉语言模型 (LVLMs) 正在推进自动驾驶,特别是在轨迹预测方面.
自动驾驶汽车的车载计算需求挑战了对资源有限系统的LVLM部署.
符号修剪可以在不需要重新培训的情况下为LVLMs提供推断速度增长,但目前的方法缺乏针对自动驾驶的特异性.

研究的目的:

为了解决自动驾驶轨迹预测中通用代币修剪的局限性.
开发一种专门的标记修剪方法,将内容和距离信息视为驾驶至关重要的信息.
为了提高车载自动驾驶系统的LVLM的效率.

主要方法:

建议使用LiDAR辅助的Token Prune (LaTP),这是基于LVLM的轨迹预测的新方法.
集成的LiDAR点数据为摄像头输入提供必要的距离信息.
开发了一个内容和距离意识的代币重要性指标,以丢弃不相关的视觉代币.

主要成果:

拉特普实现了显著的推断速度增长,截减率高达75%.
保持高预测准确度,平均位移误差 (ADE) 为2.03米.
显示了2.35%的低碰撞率 (col),超过了nuScenes数据集上的通用代币修剪基线.

结论:

LaTP有效地减少了自动驾驶中的LVLMs的计算负载.
该方法成功地集成了LiDAR数据,以增强用于轨迹预测的令牌修剪.
在现实世界的自动驾驶场景中,LaTP为部署高效准确的LVLM提供了一个有前途的解决方案.

关键词:

自动驾驶自动驾驶的自动驾驶.大视野语言模型多式联络融合是多式联络的融合方式.变压器令牌修剪变压器令牌修剪

更多相关视频

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

相关概念视频

Reducing Line Loss

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...