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: Robotic Manipulation & Deep Learning
- Exploring core manipulation tasks and key system components
- Contrasting traditional methods with learning-driven approaches
- Applying deep learning to perception, planning, and control systems
Perception Systems for Robotic Grasping
- Utilizing visual sensing and object detection for effective grasping
- Processing 3D vision data, depth information, and point clouds
- Training CNNs for precise object localization and segmentation
Strategic Grasp Planning and Detection
- Reviewing classical grasp planning algorithms
- Deriving grasp poses through data-driven and simulation-based methods
- Implementing advanced grasp detection networks like GGCNN and Dex-Net
Advanced Control and Motion Planning
- Mastering inverse kinematics and trajectory generation
- Employing learning-based motion planning and imitation learning techniques
- Applying reinforcement learning to develop manipulation control policies
ROS 2 Integration & Simulation Environments
- Configuring ROS 2 nodes for seamless perception and control integration
- Simulating robotic manipulators using Gazebo and Isaac Sim
- Connecting neural models for real-time operational control
End-to-End Learning Frameworks
- Unifying perception, policy, and control within integrated networks
- Leveraging demonstration data for supervised policy training
- Managing domain adaptation between simulation and physical hardware
Performance Evaluation & Optimization
- Assessing grasp success, stability, and precision through key metrics
- Testing system robustness under varying conditions and disturbances
- Compressing models and deploying them on edge devices
Capstone Project: Deep Learning-Driven Robotic Grasping
- Architecting a complete perception-to-action pipeline
- Training and validating a specialized grasp detection model
- Integrating the learned model into a simulated robotic arm environment
Requirements
- A strong grasp of robotics kinematics and dynamics
- Proficiency with Python and deep learning frameworks
- Familiarity with ROS or equivalent robotic middleware
Target Audience
- Robotics engineers building intelligent manipulation systems
- Perception and control specialists focused on grasping applications
- Researchers and advanced practitioners in robot learning and AI-based 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.
