We propose enhancing trajectory optimization methods through the incorporation of two key ideas: variable-grasp pose sampling and trajectory commitment. Our iterative approach samples multiple grasp poses, increasing the likelihood of finding a solution while gradually narrowing the optimization horizon towards the goal region for improved computational efficiency. We conduct experiments comparing our approach with sampling-based planning and fixed-goal optimization. In simulated experiments featuring 4 different task scenes, our approach consistently outperforms baselines by generating lower-cost trajectories and achieving higher success rates in challenging constrained and cluttered environments, at the trade-off of longer computation times. Real-world experiments further validate the superiority of our approach in generating lower-cost trajectories and exhibiting enhanced robustness. While we acknowledge the limitations of our experimental design, our proposed approach holds significant potential for enhancing trajectory optimization methods and offers a promising solution for achieving consistent and reliable robotic manipulation.

翻译：我们提出通过融合两个关键思想来增强轨迹优化方法：可变抓取姿态采样与轨迹承诺。我们的迭代方法会采样多个抓取姿态，这增加了找到解决方案的可能性，同时逐步缩小优化范围至目标区域，以提高计算效率。我们进行了实验，将我们的方法与基于采样的规划以及固定目标优化进行比较。在包含4种不同任务场景的仿真实验中，我们的方法始终优于基线方法，能够在具有挑战性的受限、杂乱环境中生成成本更低的轨迹，并实现更高的成功率，但代价是计算时间更长。真实世界的实验进一步验证了我们的方法在生成低成本轨迹和增强鲁棒性方面的优越性。尽管我们承认实验设计的局限性，但所提出的方法在增强轨迹优化方法方面具有显著潜力，并为实现一致且可靠的机器人操作提供了有前景的解决方案。