Reliable and efficient trajectory optimization methods are a fundamental need for autonomous dynamical systems, effectively enabling applications including rocket landing, hypersonic reentry, spacecraft rendezvous, and docking. Within such safety-critical application areas, the complexity of the emerging trajectory optimization problems has motivated the application of AI-based techniques to enhance the performance of traditional approaches. However, current AI-based methods either attempt to fully replace traditional control algorithms, thus lacking constraint satisfaction guarantees and incurring in expensive simulation, or aim to solely imitate the behavior of traditional methods via supervised learning. To address these limitations, this paper proposes the Autonomous Rendezvous Transformer (ART) and assesses the capability of modern generative models to solve complex trajectory optimization problems, both from a forecasting and control standpoint. Specifically, this work assesses the capabilities of Transformers to (i) learn near-optimal policies from previously collected data, and (ii) warm-start a sequential optimizer for the solution of non-convex optimal control problems, thus guaranteeing hard constraint satisfaction. From a forecasting perspective, results highlight how ART outperforms other learning-based architectures at predicting known fuel-optimal trajectories. From a control perspective, empirical analyses show how policies learned through Transformers are able to generate near-optimal warm-starts, achieving trajectories that are (i) more fuel-efficient, (ii) obtained in fewer sequential optimizer iterations, and (iii) computed with an overall runtime comparable to benchmarks based on convex optimization.

翻译：可靠高效的轨迹优化方法是自主动态系统的基本需求，有效支撑了火箭着陆、高超声速再入、航天器交会与对接等应用。在此类安全关键应用领域，新兴轨迹优化问题的复杂性促使基于人工智能的技术被引入以增强传统方法性能。然而，现有AI方法要么试图完全取代传统控制算法，从而缺乏约束满足保证并导致高昂仿真成本，要么仅通过监督学习模仿传统方法行为。为突破这些局限，本文提出自主交会Transformer（ART），从预测和控制双重视角评估现代生成模型解决复杂轨迹优化问题的能力。具体而言，本研究评估Transformer的以下能力：(i) 从历史数据中学习近优策略，(ii) 为求解非凸最优控制问题的顺序优化器提供热启动，从而保证硬约束满足。预测视角的结果表明，ART在预测已知燃料最优轨迹方面优于其他基于学习的架构。控制视角的实证分析显示，通过Transformer学习的策略能够生成近优热启动，获得的轨迹具有：(i) 更高燃料效率，(ii) 所需顺序优化器迭代次数更少，(iii) 总计算耗时与基于凸优化的基准方法相当。