Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
System Integration and Path Planning on the Pepper Robot
The main objectives of this project are to perform system integration on the Pepper robot and to develop path planning algorithms based on its existing sensor suite for moving in environments with dynamic obstacles.
Keywords: mobile robots, system integration, SLAM, sensing and planning, dynamic environments, ROS
Path planning in dynamic and uncertain environments remains a challenging problem for mobile robots. Many difficulties arise in attempting to sense, model and predict the motion of dynamic obstacles that may move into the path of the robot.
The goal of this project is to implement a robust planning algorithm on Pepper, the humanoid robot developed by SoftBank Robotics, such that it can move seamlessly through environments shared with humans (e.g. in an open office space). The project will require integration of the existing hardware on the Pepper platform and development of simulation tools for rapid software validation.
Path planning in dynamic and uncertain environments remains a challenging problem for mobile robots. Many difficulties arise in attempting to sense, model and predict the motion of dynamic obstacles that may move into the path of the robot.
The goal of this project is to implement a robust planning algorithm on Pepper, the humanoid robot developed by SoftBank Robotics, such that it can move seamlessly through environments shared with humans (e.g. in an open office space). The project will require integration of the existing hardware on the Pepper platform and development of simulation tools for rapid software validation.
1. Familiarisation with the Pepper platform and its ROS interface
2. Literature review of path planning techniques in static and dynamic environments
3. Development of a planning algorithm that leverages the existing sensor suite on Pepper
4. Experimentation to evaluate the planning method in simulation and on hardware
1. Familiarisation with the Pepper platform and its ROS interface 2. Literature review of path planning techniques in static and dynamic environments 3. Development of a planning algorithm that leverages the existing sensor suite on Pepper 4. Experimentation to evaluate the planning method in simulation and on hardware
- Strong interest in mobile robotics, both in terms of algorithm development and hardware integration
- Programming skills (C++/Python)
- Experience with Linux, ROS, and typical development tools such as Git
- Strong interest in mobile robotics, both in terms of algorithm development and hardware integration - Programming skills (C++/Python) - Experience with Linux, ROS, and typical development tools such as Git
- Jen Jen Chung, jenjen.chung@mavt.ethz.ch
- Daniel Dugas, daniel.dugas@mavt.ethz.ch
- Jen Jen Chung, jenjen.chung@mavt.ethz.ch - Daniel Dugas, daniel.dugas@mavt.ethz.ch