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
Introduction to Robotic Manipulation and Deep Learning
- Overview of manipulation tasks and associated system components
- Comparison of traditional methods versus learning-based approaches
- Application of deep learning in perception, planning, and control
Perception for Manipulation
- Visual sensing and object detection tailored for grasping
- 3D vision, depth sensing, and point cloud data processing
- Training CNNs for object localization and segmentation tasks
Grasp Planning and Detection
- Review of classical grasp planning algorithms
- Learning grasp poses utilizing data and simulation
- Implementation of grasp detection networks such as GGCNN and Dex-Net
Control and Motion Planning
- Inverse kinematics and trajectory generation techniques
- Learning-based motion planning and imitation learning methods
- Reinforcement learning for developing manipulation control policies
Integration with ROS 2 and Simulation Environments
- Configuration of ROS 2 nodes for perception and control functions
- Simulating robotic manipulators using Gazebo and Isaac Sim
- Integration of neural models for real-time control operations
End-to-End Learning for Manipulation
- Combining perception, policy, and control within unified network architectures
- Utilizing demonstration data for supervised policy learning
- Domain adaptation techniques bridging simulation and physical hardware
Evaluation and Optimization
- Metrics for assessing grasp success, stability, and precision
- Testing performance under varying conditions and disturbances
- Model compression and deployment strategies for edge devices
Hands-on Project: Deep Learning-Based Robotic Grasping
- Designing a complete perception-to-action pipeline
- Training and testing a functional grasp detection model
- Integrating the developed model into a simulated robotic arm
Requirements
- A robust grasp of robotics kinematics and dynamics
- Proficiency in Python and various deep learning frameworks
- Knowledge of ROS or equivalent robotic middleware
Target Audience
- Robotics engineers focused on creating intelligent manipulation systems
- Specialists in perception and control dedicated to 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.
