中文
相关论文

相关论文: SkiP: When to Skip and When to Refine for Efficien…

200 篇论文

Real-world tasks such as garment manipulation and table rearrangement demand robots to perform generalizable, highly precise, and long-horizon actions. Although imitation learning has proven to be an effective approach for teaching robots…

机器人学 · 计算机科学 2025-07-03 Shengjie Wang , Jiacheng You , Yihang Hu , Jiongye Li , Yang Gao

The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which…

机器人学 · 计算机科学 2025-03-11 Zexin Zheng , Jia-Feng Cai , Xiao-Ming Wu , Yi-Lin Wei , Yu-Ming Tang , Wei-Shi Zheng

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

机器人学 · 计算机科学 2021-12-08 Michael James McDonald , Dylan Hadfield-Menell

Classical policy search algorithms for robotics typically require performing extensive explorations, which are time-consuming and expensive to implement with real physical platforms. To facilitate the efficient learning of robot…

机器人学 · 计算机科学 2023-04-25 Shengzeng Huo , Anqing Duan , Lijun Han , Luyin Hu , Hesheng Wang , David Navarro-Alarcon

Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human…

机器人学 · 计算机科学 2024-01-30 Jesse Zhang , Karl Pertsch , Jiahui Zhang , Joseph J. Lim

Robotic manipulation relies on analytical or learned models to simulate the system dynamics. These models are often inaccurate and based on offline information, so that the robot planner is unable to cope with mismatches between the…

机器人学 · 计算机科学 2024-03-13 Marco Faroni , Dmitry Berenson

Action representation is an important yet often overlooked aspect in end-to-end robot learning with deep networks. Choosing one action space over another (e.g. target joint positions, or Cartesian end-effector poses) can result in…

机器人学 · 计算机科学 2022-03-07 Aditya Ganapathi , Pete Florence , Jake Varley , Kaylee Burns , Ken Goldberg , Andy Zeng

Trading off performance guarantees in favor of scalability, the Multi-Agent Path Finding (MAPF) community has recently started to embrace Multi-Agent Reinforcement Learning (MARL), where agents learn to collaboratively generate individual,…

机器人学 · 计算机科学 2023-09-01 Yutong Wang , Bairan Xiang , Shinan Huang , Guillaume Sartoretti

Robot learning has proven to be a general and effective technique for programming manipulators. Imitation learning is able to teach robots solely from human demonstrations but is bottlenecked by the capabilities of the demonstrations.…

机器人学 · 计算机科学 2024-10-24 Zihan Zhou , Animesh Garg , Dieter Fox , Caelan Garrett , Ajay Mandlekar

Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization. Inspired by recent advances…

机器学习 · 计算机科学 2022-11-16 Soroush Nasiriany , Tian Gao , Ajay Mandlekar , Yuke Zhu

Autonomous robots are widely utilized for mapping and exploration tasks due to their cost-effectiveness. Multi-robot systems offer scalability and efficiency, especially in terms of the number of robots deployed in more complex…

机器人学 · 计算机科学 2025-06-04 Apoorva Vashisth , Manav Kulshrestha , Damon Conover , Aniket Bera

Mobile robots are often tasked with repeatedly navigating through an environment whose traversability changes over time. These changes may exhibit some hidden structure, which can be learned. Many studies consider reactive algorithms for…

机器人学 · 计算机科学 2020-12-07 Florence Tsang , Tristan Walker , Ryan A. MacDonald , Armin Sadeghi , Stephen L. Smith

We present a fast and effective policy framework for robotic manipulation, named Energy Policy, designed for high-frequency robotic tasks and resource-constrained systems. Unlike existing robotic policies, Energy Policy natively predicts…

机器人学 · 计算机科学 2025-10-15 Jingkai Jia , Tong Yang , Xueyao Chen , Chenhuan Liu , Wenqiang Zhang

Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properties are that do not hold in mobile manipulation. Task plans…

机器人学 · 计算机科学 2023-11-08 Priyam Parashar , Vidhi Jain , Xiaohan Zhang , Jay Vakil , Sam Powers , Yonatan Bisk , Chris Paxton

Jointly achieving safety and efficiency in human-robot interaction (HRI) settings is a challenging problem, as the robot's planning objectives may be at odds with the human's own intent and expectations. Recent approaches ensure safe robot…

机器人学 · 计算机科学 2022-03-14 Haimin Hu , Kensuke Nakamura , Jaime F. Fisac

We introduce skipping refinement, a new notion of correctness for reasoning about optimized reactive systems. Reasoning about reactive systems using refinement involves defining an abstract, high-level specification system and a concrete,…

计算机科学中的逻辑 · 计算机科学 2015-02-11 Mitesh Jain , Panagiotis Manolios

Recent advances in Behavior Cloning (BC) have made it easy to teach robots new tasks. However, we find that the ease of teaching comes at the cost of unreliable performance that saturates with increasing data for tasks requiring precision.…

机器人学 · 计算机科学 2024-12-13 Lars Ankile , Anthony Simeonov , Idan Shenfeld , Marcel Torne , Pulkit Agrawal

While imitation learning has shown impressive results in single-task robot manipulation, scaling it to multi-task settings remains a fundamental challenge due to issues such as suboptimal demonstrations, trajectory noise, and behavioral…

机器人学 · 计算机科学 2025-12-23 Yihang Zhu , Weiqing Wang , Shijie Wu , Ye Shi , Jingya Wang

Recent advances in imitation learning have enabled robots to perform increasingly complex manipulation tasks in unstructured environments. However, most learned policies rely on discrete action chunking, which introduces discontinuities at…

机器人学 · 计算机科学 2025-06-06 Dongwoo Son , Suhan Park

We present a Sequential Mobile Manipulation Planning (SMMP) framework that can solve long-horizon multi-step mobile manipulation tasks with coordinated whole-body motion, even when interacting with articulated objects. By abstracting…

机器人学 · 计算机科学 2025-08-27 Ziyuan Jiao , Yida Niu , Zeyu Zhang , Yangyang Wu , Yao Su , Yixin Zhu , Hangxin Liu , Song-Chun Zhu
‹ 上一页 1 2 3 10 下一页 ›