Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Active Sensing for Autonomous Robot Navigation
The goal of this project is to implement an active sensing path-planning strategy in order to perform autonomous navigation and exploration of a partially unknown environment and reconstruction of a scalar field of interest.
In the recent years, the use of robotic platforms has increased exponentially to a wide range of different settings and situations, such as mapping and inspection. In order to enable robots to navigate in complex, unknown and dynamic environments, they must be able to move with guaranteed safety, even when facing environments they do not have full prior knowledge of. However, the ***full autonomous navigation*** still remains a big challenge.
The aim of this project is to develop an ***active sensing planner*** that allows ***autonomous exploration*** of (partially) unknown environments in order to ***investigate a natural phenomenon*** (e.g. radiation mapping). The objective is to cover the whole area of interest in the shortest time possible, while collecting data and processing them to identify the most interesting areas to go to, such as peaks in the scalar field of interest. The path planner should be able to run online and allow safe navigation of the robot.
The goals are the following:
- Implementation of an active sensing path-planning strategy.
- Evaluation of the algorithm against other state-of-the-art planners.
- Use of the planner for the navigation of a real robot (Super Mega Bot or drone).
[1] Ghaffari Jadidi, M., Valls Miro, J. & Dissanayake, G., _Gaussian processes autonomous mapping and exploration for range-sensing mobile robots_. Auton Robot 42, 273–290 (2018)
In the recent years, the use of robotic platforms has increased exponentially to a wide range of different settings and situations, such as mapping and inspection. In order to enable robots to navigate in complex, unknown and dynamic environments, they must be able to move with guaranteed safety, even when facing environments they do not have full prior knowledge of. However, the ***full autonomous navigation*** still remains a big challenge.
The aim of this project is to develop an ***active sensing planner*** that allows ***autonomous exploration*** of (partially) unknown environments in order to ***investigate a natural phenomenon*** (e.g. radiation mapping). The objective is to cover the whole area of interest in the shortest time possible, while collecting data and processing them to identify the most interesting areas to go to, such as peaks in the scalar field of interest. The path planner should be able to run online and allow safe navigation of the robot.
The goals are the following: - Implementation of an active sensing path-planning strategy. - Evaluation of the algorithm against other state-of-the-art planners. - Use of the planner for the navigation of a real robot (Super Mega Bot or drone).
[1] Ghaffari Jadidi, M., Valls Miro, J. & Dissanayake, G., _Gaussian processes autonomous mapping and exploration for range-sensing mobile robots_. Auton Robot 42, 273–290 (2018)
- ***WP1:*** Familiarization with state-of-the-art literature on the active sensing path-planning problem.
- ***WP2:*** Implementation of an active sensing path-planning strategy.
- ***WP3:*** Evaluation of the new framework with respect to other already existing strategies.
- ***WP4:*** Design and conduct experiments with ground and/or aerial robots.
- ***WP1:*** Familiarization with state-of-the-art literature on the active sensing path-planning problem. - ***WP2:*** Implementation of an active sensing path-planning strategy. - ***WP3:*** Evaluation of the new framework with respect to other already existing strategies. - ***WP4:*** Design and conduct experiments with ground and/or aerial robots.
- Interest in Computer Sciences, Robotics and Autonomous Navigation;
- Solid mathematical background;
- C++ programming experience;
- Experience in mobile robotics, Linux, ROS is beneficial.
- Interest in Computer Sciences, Robotics and Autonomous Navigation; - Solid mathematical background; - C++ programming experience; - Experience in mobile robotics, Linux, ROS is beneficial.
Interested Students please send CV, Bachelor and Master transcripts to Luca Bartolomei (lbartolomei@ethz.ch) with CC to Nicholas Lawrence (nicholas.lawrance@mavt.ethz.ch). Do not apply on Sirop.
Interested Students please send CV, Bachelor and Master transcripts to Luca Bartolomei (lbartolomei@ethz.ch) with CC to Nicholas Lawrence (nicholas.lawrance@mavt.ethz.ch). Do not apply on Sirop.