BitTP: The Lightweight Trajectory Prediction Model with BitLLM for Edge-Devices

2026-05-28

AI Summary

This work addresses the challenge of deploying large language models (LLMs) for trajectory prediction on edge devices, where high computational and memory demands are prohibitive. To this end, we propose BitTP-Weight, the first method to transform an LLM-based trajectory predictor into a lightweight bit-linear architecture by quantizing weights to 1.58 bits while preserving full-precision activations. This approach substantially reduces memory footprint and inference latency, and simultaneously introduces a regularization effect that enhances prediction accuracy. Compared to a BF16 baseline, BitTP-Weight achieves a 14.29% reduction in average displacement error (ADE) and a 20.97% reduction in final displacement error (FDE), outperforming existing quantization strategies.

Abstract

Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large language models (LLMs) have recently been adopted for this task, as they provide strong contextual reasoning and interpretable, language-based trajectory representations. However, these LLM-based predictors are extremely memory- and compute-intensive, making them difficult to deploy on resource-constrained edge devices such as on-board computers in autonomous robots. To bridge this gap, we propose BitTP, which converts an LLM-based trajectory predictor into a lightweight bitlinear architecture. We demonstrate that weight-only quantization to 1.58-bit (BitTP-Weight) is optimal. Crucially, activations must remain in full precision, as quantizing them leads to severe degradation and instability in spatio-temporal reasoning. Empirically, BitTP-Weight not only preserves but improves prediction quality over the full-precision (BF16) LLM baseline, reducing ADE by 14.29% and FDE by 20.97% on average, while simultaneously reducing memory usage and inference latency relative to other quantization methods. These results demonstrate that carefully designed quantization acts as an effective regularizer, enabling the practical deployment of sophisticated LLM-based reasoning on edge devices. Code is available at: https://github.com/MintCat98/BitTP.

Problem

• trajectory prediction
• large language models
• edge devices
• resource-constrained deployment
• autonomous systems

Innovation

• weight-only quantization
• bitlinear
• trajectory prediction
• edge deployment
• LLM-based reasoning