核心科技

任务自适应机器视觉智能

工业自动化中视觉引导的机器人智能的主要挑战之一是目标对象的多样性和不可预测的形状。传统上,零件的可靠识别需要高度专业的定制和算法参数的仔细调整,这使得这些解决方案昂贵且难以大规模部署。我们的任务自适应机器视觉技术能够自动适应不同形状的零件。不需要自定义或参数调整。

实时确定性路径规划算法

目前最常用的路径规划算法(例如RRT或PRM)均位基于采样的方法。这种算法的行为具有一定的随机性。因此难以应用在对安全性要求很高的应用中,比如工业制造。我们的确定性路径规划算法解决了这个问题。与经典方法相比,该算法能够在极端受限的环境中实时稳定的找到可行的路径。

研究论文和专利

Bin picking (also referred to as random bin picking) is a core problem in computer vision and robotics. The goal is to have a robot with sensors and cameras attached to it pick-up known objects with random poses out of a bin using a suction gripper, parallel gripper, or other kind of robot end effector.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, June 2020

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Tianhao Zhang, Zoe McCarthy, Owen Jow, Dennis Lee, Xi Chen, Ken Goldberg, Pieter Abbeel

研究论文和专利

Bin picking (also referred to as random bin picking) is a core problem in computer vision and robotics. The goal is to have a robot with sensors and cameras attached to it pick-up known objects with random poses out of a bin using a suction gripper, parallel gripper, or other kind of robot end effector.

一种端到端的高精度工业零件形状建模方法, 专利号:ZL 2020 1 0280473.7
一种高精度图像语义分割算法模型及分割方法, 专利号:ZL 2020 1 0281360.9
一种用于工业零件测量的高精度图像语义分割方法,专利号:ZL 2020 1 0281361.3
一种基于模板的三维点云目标检测和姿态估计方法,专利号: ZL 2020 1 0287173.1
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, June 2020

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Tianhao Zhang, Zoe McCarthy, Owen Jow, Dennis Lee, Xi Chen, Ken Goldberg, Pieter Abbeel

加入我们助力中国智能制造

我们正在招聘