New paper available - invited talk

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 addessed 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/.

New job opportunity on behaviour modelling

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.

PhD Studentships available!

We have two PhD studentships available (application deadline 31st January 2022).
More information
Apply

1. Human Activity Analysis In Smart Environments
   • Area of Research: Assisted Living, Machine Learning, Artificial Intelligence
   • Aim and Objectives: Analysing human activity has a wide variety of applications, including but not limited to human-robot interaction, security and assisted living. Although limited by some technological, economical, ethical and privacy constraints, the impact of these applications is no longer a promise for the future, but a reality. Chairs and glasses are currently being used to monitor older people’s safety to promote healthy independent living with simple sensors such as fall detectors. Autonomous cars and robots analyse pedestrian behaviour to assess risk and comfort. The main goal of the project will be to analyse behaviour based on vision sensors that allow for non-invasive analysis. When considering vision-based data acquisition methods, non-invasiveness, accuracy and privacy form a triangle where one corner is sacrificed. Methods based on markers or wearables are accurate and only gather the necessary data, but are invasive. Non-invasive methods are either of limited accuracy or prone to generate serious privacy concerns. Processing the acquired data has similar limitations in terms of accuracy, privacy and response time. The aim of the PhD will be to remove or mitigate to the greatest possible extent these limitations. The student will design and develop models to implement data acquisition and activity analysis, and evaluate how these models perform considering accuracy, response time, privacy and non-invasiveness.
2. Self-supervised Monocular Depth Estimation
   • Area of Research: Computer Vision
   • Project Summary, Aim and Objectives: This PhD project is a collaboration between Aston University and Aurrigo Ltd, a global leader in autonomous vehicle technology and manufacturer of autonomous passenger transportation systems. A detailed understanding of the 3D environment structure and the motion of dynamic objects is essential for autonomous navigation. This is usually achieved through a mixture of sensors such as Li-DAR, RADAR and cameras located around the vehicle. Recently there has been a major drive by some of the major Autonomous Vehicle (AV) manufacturers to remove their reliance on Li-DAR sensors. The reasons cited include their large size, high cost as well as lack of flexibility arising from the need to have pre-mapped Revised December 2021 environments for Li-DAR localization to work. In the last two years, several Deep Learning systems have been proposed that automatically convert a simple camera feed into a depth-map feed. However, despite promising results, these systems are not yet drop-in replacements for Li-DAR because there is a significant gap in accuracy and reliability. Our goal is to develop a monocular depth estimation technology that convincingly competes with state- of-the-art supervised methods of depth estimation as well as expensive sensor equipment (Li-DAR). To achieve this, we will leverage Aurrigo’s experience with autonomous vehicle perception systems as well as Aston’s leading research in 3D reconstruction from visual data. Alongside our main goal the PhD student will also be making contributions in the following secondary goals:
     • estimating the movement of dynamic objects in an image and the camera movement. The analysis will focus mainly on self-driving vehicles and develop a method of perception understanding for the camera.
     • the developing area of self-supervised learning to utilise more efficient learning of scenes.
     • using monocular depth estimations for scene construction and scene understanding.
     • making a detailed comparison between human perception and camera perception.

PhD Studentship on Ethics-aware Cognitive Architectures for Ambient Intelligence (UK applicants only)

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.

RoboComp in Google Summer of Code 2020

New project section: SNGNN

MDPI Special Issue of Applied Sciences on Cognitive Robotics

PhD Studentship position: Deep Learning in Graph Domains for Sensorised Environments (re-opened)

PhD Studentship position: Deep Learning in Graph Domains for Sensorised Environments

New paper in Complexity

RoboComp got accepted in Google's GSoC'19

New paper in UK-RAS-19

New paper accepted in UK-RAS 2019 Conference entitled "A Bioinspired Approach for Mental Emotional State Perception towards Social Awareness in Robotics" (Jordan J. Bird, Anikó Ekárt, Diego R. Faria and Luis J. Manso).

New paper in Cognitive Systems Research