[MA Project] Learning-Based Robot Trajectory Prediction

Type: Project

Status: open

Date: August 1, 2025 - January 31, 2026

Supervisors: Prajol Shrestha

Master Project on Learning-Based Robot Trajectory Prediction

Predicting robot trajectories is critical for safe navigation, swarm coordination, and autonomous decision-making in dynamic environments. This project focuses on developing and evaluating advanced deep learning models for trajectory prediction using sequential data from mobile robots. We will explore recurrent and attention-based architectures such as RNNs, LSTMs, Transformers, and state-of-the-art models like Mamba to build robust and accurate trajectory forecasting systems.

Your profile and skills:

  • Proficiency in Python and deep learning frameworks (PyTorch)

  • Strong interest in time-series modeling, sequential data analysis, and physics-based motion dynamics

  • Familiarity with robotics, motion planning, or control is a plus

  • Ability to work analytically and approach problems in a structured, research-oriented manner

  • Independent working style with a passion for team collaboration

  • Excellent communication skills in English

Application:
Please send your CV, transcript of records, and a short motivation letter describing your interest in robot trajectory prediction and sequential deep learning models to prajol.shrestha@fau.de with the subject line: “[Learning-Based Robot Trajectory Prediction Project Application 2025]”. Applications without these documents will not be considered.