Event-based Vision for Navigation in Autonomous Systems

Eurecom; France; On-site; EUR 25,000 - 35,000; Full time

Job summary

Eurecom is offering a CIFRE PhD thesis position focused on event-based vision for navigation in autonomous systems. The research will explore the use of event cameras for motion understanding and behavior recognition, aiming to advance the capabilities of autonomous robots and cars.

The position requires innovative approaches to leverage the unique characteristics of event cameras in real-world applications, and the contract will be under IMRA’s employment framework starting October 1st, 2026.

Responsibilities

• Investigate use of event-based cameras for motion understanding and trajectory estimation.
• Study behavior recognition of individuals in vehicle environments.

Job description

Event-based Vision for Navigation in Autonomous Systems

CIFRE PhD student - CIFRE thesis offer (Ref.: DS/JLD/event/062026)

Robots, cars as well, are expected to become increasingly autonomous and efficient in terms of navigation, thanks to a range of sensors and the associated data processing based on artificial intelligence. Among existing sensors, event-based cameras offer numerous advantages, however, they have not yet been studied extensively enough to be used in practical applications today. This thesis aims to investigate (i) their use for motion understanding, trajectory estimation, and decision-making in autonomous navigation (ii) their use for behavior recognition (detection and analysis of person’s face and body in / around vehicles, drivers, passengers, pedestrians around).

Event cameras are bio‑inspired vision sensors that represent a fundamental breakthrough compared to traditional frame‑based imaging. Rather than capturing entire frames at regular intervals, these sensors operate in an asynchronous manner, meaning that each pixel independently triggers an event only when a change in brightness exceeds a specific threshold. The properties of these cameras (alone, or jointly with RGB and/or LIDAR sensors) align with the dynamic and unpredictable characteristics of potential activities around moving cars or robots, making them particularly suited for capturing fast, irregular and unexpected actions. However, they also introduce unique challenges that require a deep rethinking of conventional vision methodologies and the use of specific neural networks.

Start date: October 1st, 2026

Type of employment contract : Thesis CIFRE EURECOM x IMRA, (IMRA employment contract , www. imra.eu/fr )