Trajectory prediction and generation are vital for autonomous robots navigating dynamic environments. While prior research has typically focused on either prediction or generation, our approach unifies these tasks to provide a versatile framework and achieve state-of-the-art performance. Diffusion models, which are currently state-of-the-art for learned trajectory generation in long-horizon planning and offline reinforcement learning tasks, rely on a computationally intensive iterative sampling process. This slow process impedes the dynamic capabilities of robotic systems. In contrast, we introduce Trajectory Conditional Flow Matching (T-CFM), a novel data-driven approach that utilizes flow matching techniques to learn a solver time-varying vector field for efficient and fast trajectory generation. We demonstrate the effectiveness of T-CFM on three separate tasks: adversarial tracking, real-world aircraft trajectory forecasting, and long-horizon planning. Our model outperforms state-of-the-art baselines with an increase of 35% in predictive accuracy and 142% increase in planning performance. Notably, T-CFM achieves up to 100$\times$ speed-up compared to diffusion-based models without sacrificing accuracy, which is crucial for real-time decision making in robotics.

翻译：轨迹预测与生成对于在动态环境中自主导航的机器人至关重要。以往研究通常侧重于预测或生成中的单一任务，而我们的方法将这两类任务统一起来，提供了一个多功能框架并实现了最先进的性能。扩散模型是目前长时域规划和离线强化学习任务中基于学习的轨迹生成的最先进方法，但其依赖计算密集的迭代采样过程，这一缓慢过程限制了机器人系统的动态能力。相比之下，我们提出了轨迹条件流匹配（T-CFM），这是一种新颖的数据驱动方法，利用流匹配技术学习求解器时变向量场，以实现高效快速的轨迹生成。我们在三个独立任务上证明了T-CFM的有效性：对抗性跟踪、真实世界飞机轨迹预测和长时域规划。我们的模型在预测精度上提升了35%，规划性能提升了142%，优于现有的最先进基线方法。值得注意的是，T-CFM在保持精度的前提下相比基于扩散的模型实现了高达100倍的加速，这对机器人领域的实时决策至关重要。