Google Scholar
GitHub
LinkedIn
ORCID: 0000-0003-3007-3553Bio sketch
I am a postdoctoral researcher at the Dynamic Legged Systems at the Istituto Italiano di Tecnologia. My research focuses on machine learning and optimal control for robot locomotion and manipulation, particularly for quadruped robots.
I received my Bachelor’s degree in Computer Engineering from the University of Pisa in 2016, and my Master’s degree in Artificial Intelligence and Robotics from Sapienza University of Rome in 2018. In 2022, I completed my PhD in Automatic Control, Bioengineering, and Operations Research at Sapienza, where I was part of the DIAG Robotics Lab.
I value open-source software, reproducible research, and teaching, and I’m always happy to discuss ideas and potential collaborations - feel free to send an email!
Research
Latest publications
- SKooP: Symmetric koopman predictions for faster and more generalizable legged robot locomotion with reinforcement learning
E D'Elia, W Zhan, G Turrisi, G Romualdi, G L'Erario, R Camoriano, W Pan, ...
2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 - Mixture-of-Experts RL for fault-tolerant legged locomotion
G Turrisi, O Pali, L Oneto, C Semini
arXiv preprint arXiv:2606.25965, 2026 - BinWalker: Development and field evaluation of a quadruped manipulator platform for sustainable litter collection
G Turrisi, A Bratta, G Minelli, GF Abati, AH Rad, JCV Soares, C Semini
2026 IEEE/ASME International Conference on Advanced Intelligent Mechatronics …, 2026 - Proprioceptive image: An image representation of proprioceptive data from quadruped robots for contact estimation learning
GF Abati, JCV Soares, G Turrisi, V Barasuol, C Semini
2026 IEEE International Conference on on Robotics and Automation (ICRA), 2026 - Feedback-MPPI: Fast sampling-based MPC via rollout differentiation--Adios low-level controllers
T Belvedere, M Ziegltrum, G Turrisi, V Modugno
IEEE Robotics and Automation 11 (1), 1-8, 2026 - Primal-dual iLQR for GPU-accelerated learning and control in legged robots
L Amatucci, J Sousa-Pinto, G Turrisi, D Orban, V Barasuol, C Semini
IEEE Robotics and Automation Letters 11 (1), 1010-1017, 2026 - CroSTAta: Cross-state transition attention transformer for robotic manipulation
G Minelli, G Turrisi, V Barasuol, C Semini
arXiv preprint arXiv:2510.00726, 2025 - BC-MPPI: A probabilistic constraint layer for safe model-predictive path-integral control
O Ezeji, M Ziegltrum, G Turrisi, T Belvedere, V Modugno
Agents and Robots for reliable Engineered Autonomy (AREA) 2700, 131–143, 2025 - Guided reinforcement learning for omnidirectional 3D jumping in quadruped robots
R Bussola, M Focchi, G Turrisi, C Semini, L Palopoli
arXiv preprint arXiv:2507.16481, 2025 - Adaptive non-linear centroidal MPC with stability guarantees for robust locomotion of legged robots
M Elobaid, G Turrisi, L Rapetti, G Romualdi, S Dafarra, T Kawakami, ...
IEEE Robotics and Automation Letters 10 (3), 2806-2813, 2025
Teaching
TODO
Software
Selected open-source projects from my GitHub profile
iit-DLSLab/Quadruped-PyMPC ★ 523
A model predictive controller for quadruped robots based on the single rigid body model and written in python. Gradient-based (acados) or Sampling-based (jax)
iit-DLSLab/basic-locomotion-isaaclab ★ 131
An IsaacLab DirectEnv for basic quadrupedal locomotion tasks, with support for multiple quadruped robots, sim-to-sim, and sim-to-real pipelines
iit-DLSLab/sim2real-robot-identification ★ 84
A joints calibration routine for quadrupeds and manipulators to facilitate sim-to-real transfer from isaaclab and mujoco to real robots
iit-DLSLab/gym-quadruped ★ 80
Mujoco Gym environment for the control of quadruped robots
iit-DLSLab/morphosymm-rsl-rl ★ 33
Extension of RSL-RL for using Morphological Symmetries in IsaacLab
iit-DLSLab/locomanipulation-teleop-isaaclab ★ 32
An IsaacLab DirectEnv for performing teleoperation with Unitree Go2 + AgileX Piper, with support for sim-to-sim and sim-to-real pipelines