CAREER: Manipulation of Novel Objects via Non-Smooth Implicit Learning
CAREER: Manipulation of Novel Objects via Non-Smooth Implicit Learning
批准号:
2238480
负责人:
Michael Posa
金额:
$60.0万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2023
资助国家:
美国
项目状态:
未结题
起止时间:
2023-04-01 至 2028-03-31
中文摘要
这个学院早期职业发展(CAREAGE)项目将创造受物理启发的学习方法,用于对新对象进行数据高效的机器人操作-即机器人事先不知道的以前未见过的对象。这一结果将使未来几代机器人能够在人类用户的日常生活中提供有意义的帮助。要做到这一点,机器人必须能够通过物理交互快速了解周围环境,特别是在超出精心控制的实验室条件的混乱环境中。这将要求机器人获得超出当前技术水平的新能力。该项目将使机器人能够确定周围物体的关键特征--尽管形状、大小、颜色和材料不同--例如它们被触摸时是否移动,它们是软的还是硬的,以及它们是弯曲还是扭曲。机器人应该能够第一次进入房间,简单地调查房间里的物体,然后安全地完成分配的任务。例如,居家机器人可能会在厨房里移动,遇到新的食物或烹饪工具,然后与这些物品互动,帮助准备一顿饭。该项目将推进一系列改善生活的机器人应用,包括家庭辅助护理、危险的搜索和救援行动,或小规模制造。为了培训和激励下一代工程师,研究人员将与费城公立学区的教育工作者合作,开发一个教育单元,利用机器人模拟器来演示高中代数中的概念。这个项目将非光滑动力学、学习和控制的概念结合在一起,使机器人能够使用从混乱环境中实时收集的数据,对以前看不到的物体进行灵活操作。例如,机器人可能会与一组新颖的物体进行最多几秒钟或几分钟的交互,然后以人类一样的灵巧精确地执行复杂的任务,如使用工具或手中操作。对这个项目的需求首先是由于功能机器人对机器人与其环境之间的相互作用的依赖,这是出了名的难以建模,其次是对基于模型和模拟现实的控制方法的预测模型的依赖。该项目通过将非光滑行为的所有来源收集到一组接触力中来解决不连续接触驱动的动力学建模问题。隐式损失函数本身使用凸优化来估计非光滑接触力,它可以使用基于梯度的方法来最小化,以找到一组描述机器人-物体相互作用的物理参数。为了提供机器人与世界交互的高效数据学习,本项目探索了以下三个主要研究主题:(1)开发具有物理启发结构的基础性内隐学习框架,用于预测机器人与世界的交互;(2)通过将触觉和视觉传感与运动预测相结合来动态操纵新的刚体和软体对象;以及(3)将这两个学习系统与控制和强化学习相结合,以实现闭环性能。总而言之,这些推力将在处理新对象时提供新的机器人能力,涉及一系列操作任务,包括手部操作和对象重新定位,全身操作(使用肢体、躯干和其他身体部位)来机动、推动和拖动重物,以及多臂操作大型或笨重的对象。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。
英文摘要
This Faculty Early Career Development (CAREER) project will create physics-inspired learning methods for data-efficient robotic manipulation of novel objects – that is, previously unseen objects about which the robot has no prior knowledge. The result will enable future generations of robots to provide meaningful assistance throughout the daily lives of human users. To achieve this, robots must be able to quickly learn about their surroundings through physical interactions, particularly in chaotic settings beyond carefully controlled laboratory conditions. This will require robots to gain new capabilities beyond the current state of the art. This project will provide robots with the ability to determine critical characteristics of surrounding objects -- despite variations in shape, size, color, and material -- such as whether they move when touched, whether they are soft or stiff, and whether they bend or twist. A robot should be able to enter a room for the first time, briefly investigate the objects in that room, and then safely accomplish an assigned task. For example, an in-home robot might maneuver about a kitchen, encountering new food items or culinary tools, and then interact with those items to help prepare a meal. This project will advance a range of life-improving robotic applications, including in-home assistive care, dangerous search and rescue operations, or small-scale manufacturing. To train and inspire the next generation of engineers, investigators, working with educators in the Philadelphia Public School District, will develop an educational unit leveraging a robotic simulator to demonstrate concepts from high-school algebra.This project brings together concepts from non-smooth dynamics, learning, and control, to enable robots that perform dexterous manipulation of previously unseen objects, using data gathered in real time from a cluttered environment. For example, a robot may interact with a set of novel objects for at most a few seconds or minutes, then precisely perform, with human-like dexterity, complex tasks such as tool use or in-hand manipulation. The need for this project is driven first by the dependence of functional robotics on interaction between the robot and its environment, which is notoriously difficult to model, and second, by the reliance on predictive models of both model-based and sim-to-real methods for control. This project addresses the modeling of discontinuous contact-driven dynamics by gathering all sources of non-smooth behavior into a set of contact forces. An implicit loss function, which itself uses convex optimization to estimate non-smooth contact forces, can be minimized using gradient-based methods to find a set of the smooth parameters that describe the physics of robot-object interactions. To provide data-efficient learning of robot-world interaction, this project explores the following three primary research thrusts: (1) development of foundational implicit-learning frameworks with physics-inspired structure for predicting robot-world interactions, (2) dynamic manipulation of novel rigid and soft objects by unifying tactile and visual sensing with motion prediction, and (3) combining these two learning systems with control and reinforcement learning for closed-loop performance. Together, these thrusts will provide new robotic capabilities when dealing with novel objects, across a range of manipulation tasks including in-hand manipulation and object reorientation, whole-body manipulation (using limbs, torso, and other body parts) to maneuver, push, and drag heavy objects, and multi-arm manipulation of large or unwieldy objects.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
期刊论文(3)
专著(0)
科研奖励(0)
会议论文
Im2Contact: Vision-Based Contact Localization Without Touch or Force Sensing
Im2Contact:基于视觉的接触定位,无需触摸或力感应
DOI:
--
发表时间:
2023
期刊:
Proceedings of Machine Learning Research
影响因子:
--
作者:
[Kim, Leon, Li, Yunshuang, Posa, Michael, Jayaraman, Dinesh]
通讯作者:
Jayaraman, Dinesh
DOI:
--
发表时间:
2023
期刊:
Proceedings of Machine Learning Research
影响因子:
--
作者:
[Bianchini, Bibit, Halm, Mathew, Posa, Michael]
通讯作者:
Posa, Michael
DOI:
10.48550/arxiv.2310.09893
发表时间:
2023-10
期刊:
ArXiv
影响因子:
--
作者:
[Wei-Cheng Huang;Alp Aydinoglu;Wanxin Jin;Michael Posa]
通讯作者:
Wei-Cheng Huang;Alp Aydinoglu;Wanxin Jin;Michael Posa
Travel Funds for 15th Dynamic Walking Conference; Hawley, Pennsylvania; May 11-14, 2020
-
批准号:2017660
-
项目类别:Standard Grant
-
资助金额:$1.0万
-
财政年份:2020
-
负责人:Michael Posa
-
依托单位:
EFRI C3 SoRo: 3-D surface control for object manipulation with stretchable materials
-
批准号:1935294
-
项目类别:Standard Grant
-
资助金额:$200.0万
-
财政年份:2020
-
负责人:Michael Posa
-
依托单位:
NRI: FND: Contact-aware Control of Dynamic Manipulation
-
批准号:1830218
-
项目类别:Standard Grant
-
资助金额:$50.49万
-
财政年份:2018
-
负责人:Michael Posa
-
依托单位:
海外基金