Ph.D. Student / Postdoc in Multi-Goal Task Planning

Combining task with motion planning – zhat’s that about? In a nutshell, multi-goal task planning has been an optimization question in Operation Research and Logistics for a long time. We are working on novel advances for high-speed solving these discrete planning problems. Our task as researchers (including you) is to develop methods that effectively combine these techniques for reasoning and acting in robotic environments.

While the discrete multi-goal task planning problem is already hard, the "physical" motion planning problem is even more demanding. The integration of task and motion planning is considered one the most important problems in robotics nowadays. Robots have sizes, heading, and velocity, and their motion can often be described only according to non-linear differential equations. The dynamics of movements, existing obstacles and many waypoints to visit are only some of the challenges to face. In real-world problems, we often have additional constraints like inspecting areas of interest in some certain order, while still minimizing the time for the travel.

The trickiest part is to solve the hard combinatorial discrete tasks like the generalized and clustered traveling salesman problems, and - at the same time - providing valid trajectories for the robot.

We extend a framework in which a motion tree is steadily grown, and abstractions to discrete planning problems are used as a heuristic guidance for the on-going solution process to eventually visit all waypoints. In case of inspection, we generate the waypoints fully automatically, using a combination of skeletonization methods together with a filtering mechanism based on hitting sets.

Robots used for inspection or moving of goods are also often required to visit certain locations subject to time and resource consumption. This requires not only planning collision-free and dynamically feasible motions, but also reasoning about constraints. To effectively solve this open problem, we couple task planning over a discrete abstraction with sampling-based motion planning over the continuous state space of feasible motions. The discrete abstraction is obtained by imposing a roadmap that captures the connectivity of the free space. We increase the expressiveness and scalability of the approach, as we raise the number of goals and the difficulty of satisfying the time and resource constraints.

With our technology we are able to efficiently generate and execute long-term missions in real-time. The robot, the environment model, and the planning problem specification can be modified non-intrusively, essential in many application scenarios. Other topics of interest are robot planning with limits in energy consumption.

Application potential

Multi-goal task-motion planning is not a stand-alone research area that lives solely in a lab. There are a number of possible collaborations in the AI Center at the Czech Technical University in Prague and applications including video games, longer-term autonomous systems, emergency management and more. Let us steer the robots of the 21st century. Sounds exciting? Reach out to us and let’s design a suitable research topic together.

Hiring process

Fill out the application form at the end of this page and we will get back to you shortly. You can also reach out to Stefan Edelkamp who is the Principal Investigator of this project. You can either apply for the postdoc position – in that case you probably know the drill – or to become a PhD Student. More info on that follows.

Ph.D. program in AIC

Our Ph.D. is designed for the period of 4 years in which you will do research in a lab, publish papers, travel to conferences, teach in classes, popularize your field and do everything that means to be a full researcher.

You can also join our center for a test run before actually applying for the Ph.D. study program. That’s honestly the best way to get to know our team, explore the research area in more depth, earn some extra money and have useful admin support to assist you with the official application process. We will have your back! Don’t wait any longer and get in touch via the application form.

Perks of being a Ph.D. student in AIC

Successful candidates will get a full tuition waiver and 45 000 CZK monthly brutto income (the equivalent of 1 670 EUR). Note that the Czech Republic's cost of living is at 59% of the US price level by OECD statistics. To give you a better idea, the average price of beer in Prague is 1,3 EUR. Cheers to that! With 6 weeks of paid vacation, you will have plenty of time to explore the cozy pubs and vibrant nightlife.

Also, get excited for traveling to attractive conferences abroad, regular internal seminars, an unlimited supply of coffee (very appreciated) and meal vouchers. Our labs are located on the university campus in the historical city center, so perfect transport accessibility is another obvious advantage.

However, what we appreciate the most about our research center is an inspirational and supportive environment. Plus you will have the convenience of working in teams where everyone knows their agenda and the supervisor is at your fingertips to help. With that said, getting your Ph.D. in AI Center FEE CTU will be a forming life experience that will kick off your research career.

Requirements

• Master degree in Computer Science
• Background in Artificial Intelligence
• Solid programming skills (C++, Python, ...)
• Solid English knowledge (both written and spoken –⁠ we are an international group of researchers)
• Ability to conduct work both individually and in a team
  

Contact

If you decide to embark on your exciting academic journey with the Automated Planning group, you will be supervised by Stefan Edelkamp. Reach out to him if you want to talk more before applying. Otherwise, go ahead and apply directly!