Smail Ait Bouhsain

Postdoctoral Researcher at Inria Paris.

photo_cv.jpg
📍 Paris, France

I am a research scientist in AI and Robotics. I am currently a postdoctoral researcher at Inria in Paris, working with Dr. Shizhe Chen and Dr. Justin Carpentier on Embodied Perception and Real-to-Sim approaches. I hold a PhD in Computer Science from LAAS-CNRS, advised by Dr. Rachid Alami and Dr. Thierry Simeon. My doctoral research focused on developing deep learning methods for multi-robot task and motion planning, more specifically, how to allow multiple robot agents to plan, reason spatially, and collaborate to solve complex, long-horizon manipulation tasks. This work led to several publications in conferences such as ICLR, ICRA, IROS and ECAI.

Previously, I received my Bachelor’s and Master’s degrees from the Swiss Federal Institute of Technology in Lausanne (EPFL), where I specialized in Machine Learning and Intelligent Systems. I also worked on several projects in industry, including building multimodal deep learning systems for emotion recognition at Logitech and developing autonomous systems and planning pipelines at OCP Group. Feel free to check my CV or my LinkedIn profile for more details.

Research Interests: Applied AI, Embodied AI, Computer Vision, Robotics.

news

Jan 01, 2026 Started a postdoctoral researcher position at Inria in Paris.
Dec 02, 2025 New pre-print available: Long-Horizon Task and Motion Planning with Learning-Based Geometric Reasoning.
Apr 24, 2025 Presented my work on Geometric Reasoning Networks at ICLR 2025 in Singapore.
Apr 16, 2025 I am thrilled to share that I have successfully defended my PhD thesis, marking the culmination of years of hard work and dedication.
Jan 22, 2025 Paper accepted at ICLR 2025: Learning Geometric Reasoning Networks for Multi-Robot Task and Motion Planning.

selected publications

  1. iclr25.png
    Learning Geometric Reasoning Networks for Robot Task and Motion Planning
    Smail Ait Bouhsain, Rachid Alami, and Thierry Simeon
    In The Thirteenth International Conference on Learning Representations (ICLR), Singapore, 2025
  2. iros24.gif
    Extending Task and Motion Planning with Feasibility Prediction: Towards Multi-Robot Manipulation Planning of Realistic Objects
    Smail Ait Bouhsain, Rachid Alami, and Thierry Simeon
    In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, UAE, 2024
  3. ecai24.png
    Learning Uncertainty Tubes via Recurrent Neural Networks for Planning Robust Robot Motions
    Simon Wasiela, Smail Ait Bouhsain, Marco Cognetti, and 2 more authors
    In 27th European Conference on Artificial Intelligence (ECAI), Santiago de Compostela, Spain, 2024
  4. iros23.gif
    Simultaneous action and grasp feasibility prediction for task and motion planning through multi-task learning
    Smail Ait Bouhsain, Rachid Alami, and Thierry Simeon
    In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, USA, 2023