从击球手到玩家：在竞技人形乒乓球中分离动作执行与策略
From Hitter to Player: Separating Motor Execution and Strategy in Competitive Humanoid Table Tennis
AI总结：
本研究在竞技人形乒乓球中分离动作执行与策略，通过三步训练提升动作策略，冻结动作栈后训练的策略在比赛中表现优异，可与人类对手完成完整11分制比赛。
摘要：
竞技人形乒乓球需要两种不同的能力：执行期望的回球动作和决定将球回至何处。我们将这两个问题分离，以球的落地区域作为动作控制与策略之间的接口。（1）我们首先训练一个以期望落地区域为条件的全身动作策略，该策略通过基于模型的击球规划器和学习到的控制器，将目标映射为可执行的人形击球动作。（2）然后我们在闭环回合中通过自博弈改进动作策略，在此阶段机器人学习处理由另一个玩家生成的来球，而非仅处理预设的来球。此时落地区域仍在不考虑对手的情况下采样，因此策略在不学习游戏策略的情况下提升了执行能力。（3）最后，我们冻结整个动作栈，并训练一个击球级策略，通过竞争性自博弈选择落地区域。动作自博弈提升了回合中的落球准确率和合法回球率。更重要的是，在整个动作栈固定的情况下，仅改变目标选择策略就会导致比赛结果出现巨大差异：与中心、随机、远离对手的基线相比，学习到的策略分别赢得89%、82%和73%的得分。学习到的策略还会根据对手位置和之前的目标改变回球位置，表明自博弈学到的内容不止于瞄准固定的“好”位置。在硬件上，相同的冻结执行栈和策略接口支持与休闲人类对手完成完整的11分制比赛，包括正手和反手回球的多回合对打。
英文摘要：
Competitive humanoid table tennis requires two distinct abilities: executing a desired return and deciding where to return the ball. We separate these two problems, with the ball landing target serving as an interface between motor control and strategy. (1) We first train a whole-body motor policy conditioned on the desired landing target, which maps the target to an executable humanoid stroke through a model-based strike planner and a learned controller. (2) We then improve the motor policy through self-play in closed-loop rallies, where the robot learns to handle incoming balls generated by another player rather than only prescribed incoming balls. At this stage, the landing targets are still sampled without considering the opponent, so the policy improves its execution without learning game strategy. (3) Finally, we freeze the entire motor stack and train a stroke-level strategic policy to choose landing targets through competitive self-play. Motor self-play improves both landing accuracy and legal-return rate during rallies. More importantly, with the entire motor stack fixed, changing only the target-selection policy leads to large differences in game outcomes: the learned strategy wins 89%, 82%, and 73% of points against center, random, and away-from-opponent baselines, respectively. The learned strategy also changes where it sends the ball according to the opponent's position and the previous target, showing that self-play learns more than simply aiming at fixed "good" locations. On hardware, the same frozen execution stack and strategic interface support complete 11-point games against a recreational human opponent, including multi-stroke rallies with both forehand and backhand returns.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
