Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Foundations of Robotic Manipulation and Deep Learning
- Survey of manipulation tasks and system architecture
- Comparison of traditional versus learning-based methods
- Role of deep learning in perception, planning, and control
Perception Capabilities for Manipulation
- Visual sensing and object detection tailored for grasping
- 3D vision, depth acquisition, and point cloud analysis
- Training CNNs for object localization and segmentation
Grasp Planning and Identification
- Conventional grasp planning algorithms
- Acquiring grasp poses from datasets and simulations
- Implementing grasp detection networks (e.g., GGCNN, Dex-Net)
Control Mechanisms and Motion Planning
- Inverse kinematics and trajectory generation
- Learning-based motion planning and imitation learning
- Reinforcement learning for manipulation control policies
Integration with ROS 2 and Simulation Platforms
- Configuration of ROS 2 nodes for perception and control
- Simulating robotic manipulators in Gazebo and Isaac Sim
- Incorporating neural models for real-time control
End-to-End Learning for Manipulation Tasks
- Unifying perception, policy, and control in integrated networks
- Utilizing demonstration data for supervised policy learning
- Domain adaptation between simulation and physical hardware
Evaluation and Performance Optimization
- Metrics for assessing grasp success, stability, and precision
- Testing under diverse conditions and disturbances
- Model compression and deployment on edge devices
Practical Project: Deep Learning-Driven Robotic Grasping
- Architecting a perception-to-action pipeline
- Training and validating a grasp detection model
- Integrating the model into a simulated robotic arm
Requirements
- Robust grasp of robotics kinematics and dynamics
- Proficiency with Python and deep learning frameworks
- Knowledge of ROS or equivalent robotic middleware
Intended Audience
- Robotics engineers building intelligent manipulation systems
- Perception and control experts focusing on grasping applications
- Researchers and senior practitioners in robot learning and AI-driven control
28 Hours
Testimonials (2)
Supply of the materials (virtual machine) to get straight into the excersises, and the explanation of the Ros2 core. Why things work a certain way.
Arjan Bakema
Course - Autonomous Navigation & SLAM with ROS 2
its knowledge and utilization of AI for Robotics in the Future.
