Takieddine Soualhi

AI & Robotics researcher @ Inria.

prof_pic.jpg

My name is Takieddine Soualhi (aka Taki). I am a postdoctoral research scientist in AI and Robotics at Inria Lyon, within the CHROMA team, collaborating with Laetitia Matignon, Olivier Simonin, and Jacques Saraydaryan. My current research lies at the intersection of reinforcement learning, robotics, and multi-agent coordination, with a particular interest in designing human-centered algorithms capable of operating in complex and dynamic environments.

Prior to my postdoctoral position, I completed my doctoral studies in Robotics and Computer Science at the University of Burgundy and Franche-Comté, under the supervision of Yassine Ruichek, Nathan Crombez, and Stéphane Galland. My PhD focused on applying reinforcement learning to visuomotor locomotion and navigation for mobile robots.

Before that, I obtained an M.Sc. in Robotics from Sorbonne University and a B.Sc. in Electrical Engineering (EEA) from Toulouse III University.

news

Jun 26, 2026 Our paper “Towards Socially Compliant Navigation in Deep Reinforcement Learning via Proxemics-Based Reward Modeling” has been accepted to IROS 2026!
May 24, 2026 I’ll be attending the 1st Workshop on Long-term Deployments in the Wild (LoWi), held at ICRA26 in Vienna.
Jan 23, 2026 I gave a talk on “Learning Multi-Robot Navigation via Multi-Agent Reinforcement Learning” at the 13ème Journées MAFTEC in Lyon (Villeurbanne).
Nov 20, 2025 I presented a poster on “Human-Aware Multi-Robot Navigation in Constrained Environments Using Multi-Agent Reinforcement Learning” at the 3rd NAVER LABS Europe International Workshop on AI for Robotics in Grenoble, France.
May 01, 2025 I joined the CHROMA team (Inria) as a postdoctoral researcher.

selected publications

  1. RAS
    Leveraging motion perceptibility and deep reinforcement learning for visual control of nonholonomic mobile robots
    Takieddine Soualhi*, Nathan Crombez, Alexandre Lombard, and 2 more authors
    Robotics and Autonomous Systems, 2025
  2. RA-L
    Learning decentralized multi-robot pointGoal navigation
    Takieddine Soualhi*, Nathan Crombez, Yassine Ruichek, and 2 more authors
    IEEE Robotics and Automation Letters, 2025