Summary

The aim of this internship is to define a method that finds artificial LiDAR markers both for indoor and outdoor environments and that is able to produce the free-space observed. This method will qualify the uncertainty of both the markers and the free-space. It will be implemented on a Nvidia Jetson Orin ship and on real robots.

Internship Context

SLAM (Simultaneous Localization and Mapping) is undoubtedly one of the most emblematic problems in robotics. It involves a robot in an unknown environment that creates a map and localizes itself within it, based solely on onboard perception: odometry measurements of its own motion, and detection, identification, and relative localization of landmarks to be placed in the map. Given the presence of multiple uncertainties, the problem is generally addressed in a probabilistic framework. The paradigm extends to a fleet of robots, in which case it is referred to as collaborative SLAM, and to the control of robots in order to build a highly informative map (covering the environment and reducing uncertainty), which is known as active collaborative SLAM [1,2]. The project is situated within this framework. The synthesis of high-level observations from sensor data is a key element for SLAM implementation on real robots, and the determination of the confidence on the measurement needed by a probabilistic framework is not trivial. The first goal of this internship is to define a LiDAR-based method to detect specific artificial markers, in the same way that it exists for camera detection of QR codes (e.g., Apriltags [3]). This method will need to be qualified, through a test-bench, in order to define the statistical characteristics of the measurement noise (e.g., covariance). Besides, an active SLAM strategy needs to know the explored area. Therefore, the free-space (explored space, with the differentiation between obstructions and out-of-range frontiers) needs to be characterized from the LiDAR. The second goal of the internship is to produce a free-space expressed with its uncertainty. The whole method will be evaluated on real multi-robot scenarios, both indoor and outdoor. For that, the method will be implemented on an Nvidia Jetson Orin board, for real-time execution. An optional extension is to implement and qualify a camera-based QR detection method.

Environment

The internship will take place in the RAP research team (Robotics, Action and Perception, https://www.laas.fr/en/teams/rap/) at LAAS-CNRS, in Toulouse. The research conducted by the RAP team concerns the design, prototyping, implementation and evaluation of algorithms for: visual perception; sensor-based control and navigation; interactive mobile manipulation; multi-sensor data modeling and fusion. As a robotics team, the addressed issues are: the uncontrolled, dynamic and evolving nature of environments and perceptual conditions; uncertainty management; real-time processing requirement; embedding of algorithms, possibly of their hardware support; reproducibility of results.

LAAS’ research activities fall within the domain of Information Sciences and Technologies and address complex systems (artificial and sometimes natural) generally heterogeneous, and at different scales, to devise theories, methodologies and tools for modeling, designing and controlling them.

Profile

[Expected] The candidate should hold a bachelor's degree in robotics, engineering, computer science (or related fields), and must pursue a master's degree or an engineering degree in the same fields.

[Expected] Good programming skills (at least one of Python, C++, and Rust).

[Expected] Good knowledge of machine learning and computer vision techniques.

[Expected] Interest in the field of robotics or computer vision.

[Appreciated] Knowledge of robotics and data fusion would be a plus.

Application

Candidates should provide a resume, a motivation letter and Master grades (both Master 1 and 2). After reviewing these documents, a possible interview will be offered to the candidate so that he or she can present his or her experiences and motivation for the subject, as well as a discussion on the subject. The interview may be held in French or English, at the candidate's choice. Applications will be studied on a rolling basis.

LAAS is in a restricted zone (Zone à régime restrictif, ZRR). The selected candidate will need to be approved by the Ministry. If the candidate is rejected, there is no possibility to pursue the internship.

References

[1] P.-Y. Lajoie, B. Ramtoula, F. Wu, and G. Beltrame, “Towards collaborative simultaneous localization and mapping: A survey of the current research landscape,” Field Robotics, vol. 2, pp. 971–1000, 2022.

[2] M. F. Ahmed, K. Masood, V. Fremont, and I. Fantoni, “Active slam: A review on last decade,” Sensors, vol. 23, no. 19, 2023.

[3] J. Kallwies, B. Forkel, and H.-J. Wuensche, “Determining and improving the localization accuracy of apriltag detection,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 8288–8294, 2020.