Talk by: Alessandro Renzaglia (CITI)

Title: Combining Stochastic Optimization and Frontiers for Aerial Multi-Robot Exploration of 3D Terrains

Keywords: Multi-robot systems, autonomous exploration, distributed systems

In this talk, I will present a novel path planning algorithm for the autonomous exploration of 3D environments with a fleet of cooperating aerial vehicles. The proposed decentralized approach, which alternates derivative-free stochastic optimization and a frontier-based algorithm, allows each robot to generate its trajectory based on the collected data and the local map built by integrating the information shared by its teammates. Whenever the system reaches a local optimum, which corresponds to a location surrounded by already explored areas, the algorithm identifies the closest frontier to get over it and restarts the local optimization. Its low computational cost and the capability to deal with constraints and decentralized decision-making make it particularly suitable for multi-robot applications in complex 3D environments. Simulation results show that this approach can generate feasible trajectories driving multiple robots to explore realistic environments. Furthermore, in terms of exploration time, this algorithm significantly outperforms a standard solution based on closest frontier points while providing similar performances compared to a computationally more expensive centralized greedy solution. A short discussion on future directions and open questions will conclude this talk.

Speaker bio:

Genoveva Vargas-Solar (http://www.vargas-solar.com) is a principal scientist of the French Council of Scientific Research (CNRS) and a member of the DataBase group of Laboratory on Informatics on Image and Information Systems (LIRIS). She is a regular member of the Mexican Academia of Computing(AMEXCOMP). In 2014 she obtained her Habilitation à Diriger des Recherches (HDR – tenure) from Univ. of Grenoble. In 2000. She obtained her first PhD degree in Computer Science at Univ. Joseph Fourier and in 2005 her second PhD degree in Literature at Univ. Stendhal. She has obtained  two Master Degrees (1997, 1998) in Computer Science at Univ. Joseph Fourier and in Compared Literature at Univ. Stendhal. She did her undergraduate studies on Computer Systems Engineering at Universidad de las Américas in Puebla, Mexico.
She contributes to the construction of service-based database/data science management systems. The objective is to design data science workflows, new queries, and enactment services guided by Service Level Objectives (SLO). She proposes query evaluation methodologies, algorithms, and tools for composing, deploying, and executing data science functions on just in time architectures (disaggregated data centres). She conducts fundamental and applied research activities for addressing these challenges on different architectures ARM, raspberry, cluster, cloud, and HPC. Her research interests in Literature concern middle age Literature, myths’ critics and myths’ analysis applied to different myths of origins. She has coordinated several research projects in Europe and Latin America financed by governments and industrial partners. She promotes gender equality and diversity and inclusion (DnI) actions. She is a member of the gender equality committee at LIRIS and she represents EDBT in the inter-conference group DnI databases. She leads the SINFONIA and JOWDISAI projects on women’s work in AI and DS. She actively promotes the scientific cooperation in Computer Science between Latin America and Europe particularly between France and Mexico and Brazil.