About

Jilles Dibangoye is a leading researcher at the intersection of robotics, autonomous systems, and machine learning, with a focus on enabling intelligent vehicles and multi-robot teams to operate safely and efficiently in complex, dynamic environments. His work spans three core areas: learning from demonstration for autonomous driving, multi-robot exploration and coverage in 3D terrains, and neural-enhanced control for aerial robots. Dibangoye’s major contributions include pioneering a framework that models driver behavior from demonstrations using spatiotemporal lattices, a method that replaces costly hand-tuning with data-driven cost function learning (24 citations). He also developed a decentralized approach combining stochastic optimization and frontier-based methods for aerial multi-robot exploration, allowing fleets of drones to efficiently map unknown 3D environments (16 and 12 citations). More recently, he has advanced quadrotor control through neural-enhanced autopilots that adapt to complex nonlinear dynamics, and introduced LAPTNet-FPN, a multi-sensor fusion network for real-time semantic grid prediction critical for navigation and tracking. With a growing citation impact and a portfolio of innovative solutions, Dibangoye is shaping the future of autonomous robotics, making his work essential reading for students and researchers in intelligent systems.

Research Focus

Key Achievements

3
H-Index
6
Papers
61
Total Citations
10
Avg Citations/Paper
🏆 Most Cited Paper
Modeling Driver Behavior from Demonstrations in Dynamic Environments Using Spatiotemporal Lattices
24 citations · 2018
📈 Most Prolific Year: 2023 (2 Papers)
🤝 Key Collaborators: 13
🏛 Institutions: Université Grenoble Alpes, Institut national de recherche en sciences et technologies du numérique, Institut National des Sciences Appliquées de Lyon, Université Claude Bernard Lyon 1

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago