On Friday 11th of September I delivered a seminar on Social Robot Navigation at Politecnico di Torino as part of their Autonomous Service Robotics Summer School. I presented the goal of Social Robot Navigation, the current challenges, and our work on Social Robot Navigation benchmarking.
After quite a few months of work, I have a new pre-print to share: Towards Data-driven Metrics for Social Robot Navigation Benchmarking. When benchmarking social navigation algorithms, research papers use either a handful of metrics (frequently 2 or 3) that disregard most of the relevant aspects of social robot navigation, or a larger set that complicates decision-making while still failing to capture key factors. We suggest taking the bitter lesson and adopting learned metrics for social robot navigation. While the dataset still requires scaling, the current model is usable for tasks that fall within its data conditions — such as go-to tasks in rooms up to 10 m² and speeds up to 2 m/s.
We are open to collaborations to scale the dataset and/or improve the model. GitHub repository: github.com/SocNavData/SocNav3/
Also recently, I gave an invited talk in the ECMR'25 workshop Advances and Challenges in Robot Social Navigation where I addressed the paper and other topics related to social robot navigation. If you want to have a look at the slides, they are publicly available: https://ljmanso.github.io/ecmr25/.
We are seeking a highly motivated and skilled Data Scientist to join our research team as a Knowledge Transfer Partnership (KTP) Associate. This exciting opportunity involves collaborating with researchers at Aston University and Legrand Care to develop innovative solutions in user behaviour modelling for fall prediction. The successful applicant will play a crucial role in advancing knowledge and making a real-world impact in healthcare technology.
Both MSc and PhD applicants are welcome to apply for this 30 month post.
Do not hesitate to ask if you have any questions!
Application link: https://jobs.aston.ac.uk/Vacancy.aspx?ref=0429-23.
We have two PhD studentships available (application deadline 31st January 2022).
More information
Apply
The selected candidate will study ambient intelligent systems, focusing on the artificial intelligence models and the cognitive architectures required to provide the services that we aim for. This will be done while accounting for the aforementioned economic and societal issues. Edge computing will be leveraged for privacy and energy efficiency purposes. Data curation and model auditing will be carefully studied and implemented to prevent systemic biases.
The student will deliver a cognitive architecture encompassing a series of state-of-the-art subsystems for perception, planning, user profiling and actuation, as well as a number of technology demonstrators to showcase the benefits of ethical ambient intelligence and the positive impact that it could have on our future society.
Interested? Read more: https://jobs.aston.ac.uk/Vacancy.aspx?ref=R210156.
If you have any questions, contact me at l.manso@aston.ac.uk.