Brief Course Description 课程简介
This course will introduce you to many of the foundational planning, control, and perception algorithms in robotics through the lens of robotic manipulation. You will implement each of these algorithms in a simplified context in Matlab. Then, you'll implement something more realistic in OpenRAVE, a simulation and planning toolchain used in the robotics manipulation research community. The focus will be on understanding and applying the ideas in new ways. There will be an end-of-semester project where you can show off what you've learned.
本课程将从机器人操作的角度向您介绍机器人技术中的许多基础规划、控制和感知算法。您将在 Matlab 的简化环境中实现这些算法。然后,您将在 OpenRAVE 中实现更现实的东西,OpenRAVE 是机器人操作研究社区中使用的模拟和规划工具链。重点是以新的方式理解和应用这些想法。将有一个学期末项目,您可以在其中展示您所学到的知识。
We will study most of the following topics (subject to change; see schedule tab above):
我们将研究以下大部分主题(可能会发生变化;请参阅上面的时间表选项卡):
- Kinematics/zero-order control
运动学/零阶控制- Representation of rotation
旋转的表示 - Manipulator forward kinematics
机械手正向运动学 - Manipulator differential kinematics
机械手微分运动学 - Cartesian end-effector control
笛卡尔末端执行器控制
- Representation of rotation
- Planning, Control 规划、控制
- Sample-based planning methods (RRT, PRM)
基于样本的规划方法(RRT、PRM) - Trajectory optimization methods
轨迹优化方法 - Markov Decision Processes
马尔可夫决策过程 - Linear optimal control (LQR, TVLQR)
线性最优控制(LQR、TVLQR)
- Sample-based planning methods (RRT, PRM)
- Filtering, Localization, and Mapping
过滤、本地化和映射- Kalman filter, EKF 卡尔曼滤波器、EKF
- SLAM algorithms SLAM算法
- Computer Vision, Perception in Point Clouds
计算机视觉、点云感知- Point cloud methods: RANSAC, ICP, etc.
点云方法:RANSAC、ICP等 - Object Detection Using Deep Learning
使用深度学习进行物体检测 - Other applications of Deep Learning
深度学习的其他应用
- Point cloud methods: RANSAC, ICP, etc.
课程地址:CS 4335/5335:机器人科学与系统(2019 年春季) --- CS 4335/5335: Robotics Science and Systems (Spring 2019)