FBGA: A Forward-Backward Method for Online Time-Optimal Velocity Planning with Generic Acceleration Constraints

Authors

Mattia Piazza, Mattia Piccinini, Sebastiano Taddei, Francesco Biral, Enrico Bertolazzi

Year

2026

Conference Paper

Algorithm

FBGA

Source

German Robotics Conference

Identifiers

DOI 10.1109/LRA.2025.3643297

Abstract¶

We present FBGA, a new algorithm for time-optimal velocity planning under generic acceleration constraints. By extending previous forward-backward approaches to handle custom acceleration constraints, our FBGA matches the accuracy of optimal control baselines while being up to three orders of magnitude faster. Our open-source C++ implementation is available at: https://github.com/DRIVEWISE/FBGA.

Summary¶

Extends forward-backward velocity planning to generic, speed-dependent acceleration envelopes such as g-g-v diagrams. FBGA closely matches optimal-control lap times while reducing full-lap computation to milliseconds, making high-fidelity speed planning practical inside online sampling-based planners.