机构
*
Xi’an Jiaotong University(西安交通大学)
;
School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院)
;
University of Western Australia(西澳大学)
Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models
Mantis:Mamba原生微调在3D点云基础模型中的高效性
Zihao Guo, Jihua Zhu, Jian Liu, Ajmal Saeed Mian
机构
*
Xi’an Jiaotong University(西安交通大学)
;
School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院)
;
University of Western Australia(西澳大学)
机构
*
Department of Statistical Sciences, University of Padua(帕多瓦大学统计科学系)
;
School of Industrial and Systems Engineering, Georgia Institute of Technology(佐治亚理工学院工业与系统工程学院)
机构
*
College of Information Science and Electronic Engineering, Zhejiang University(浙江大学信息科学与电子工程学院)
;
Department of Electrical and Electronic Engineering, The University of Hong Kong(香港大学电子与电气工程系)
;
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院)
机构
*
Dongguan Key Laboratory of Intelligent Equipment and Smart Industry, School of Advanced Engineering, Great Bay University(东莞智能装备与智能制造重点实验室,先进工程学院,大湾大学)
;
Chair of Applied Statistics, Technische Universität Dresden(应用统计学教授职位,德累斯顿技术大学)
;
Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)(可扩展数据解析与人工智能中心(ScaDS.AI))
;
College of Automation, Guangdong University of Technology(自动化学院,广东技术大学)
专题命中
点云
:point cloud(abstract);分类 cs.CV、cs.RO
AI总结
本文提出MTA-RL框架,通过多模态Transformer-based 3D affordances和强化学习实现可靠的城市自动驾驶,提升样本效率和稳定性,优于现有基线方法。
机构
*
The Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing(中国科学院航空航天信息研究所,北京)
;
The School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing(中国科学院大学电子电气与通信工程学院,北京)
;
The Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China(香港城市大学计算机科学系,香港特别行政区,中国)