Planning with learned dynamics models offers a promising approach toward versatile real-world manipulation, particularly in nonprehensile settings such as pushing or rolling, where accurate analytical models are difficult to obtain. However, collecting training data for learning-based methods can be costly and inefficient, as it often relies on randomly sampled interactions that are not necessarily the most informative. Furthermore, learned models tend to exhibit high uncertainty in underexplored regions of the skill space, undermining the reliability of long-horizon planning. To address these challenges, we propose ActivePusher, a novel framework that combines residual-physics modeling with uncertainty-based active learning, to focus data acquisition on the most informative skill parameters. Additionally, ActivePusher seamlessly integrates with model-based kinodynamic planners, leveraging uncertainty estimates to bias control sampling toward more reliable actions. We evaluate our approach in both simulation and real-world environments, and demonstrate that it consistently improves data efficiency and achieves higher planning success rates in comparison to baseline methods. The source code is available at https://github.com/elpis-lab/ActivePusher.

翻译：利用学习到的动力学模型进行规划，为实现通用的真实世界操作提供了一种有前景的途径，特别是在诸如推动或滚动等非抓取操作场景中，因为在这些场景中难以获得精确的解析模型。然而，为基于学习的方法收集训练数据可能成本高昂且效率低下，因为它通常依赖于随机采样的交互，而这些交互不一定是最具信息量的。此外，学习到的模型在技能空间未被充分探索的区域往往表现出较高的不确定性，从而损害了长时域规划的可靠性。为应对这些挑战，我们提出了ActivePusher，这是一个新颖的框架，它将残差物理建模与基于不确定性的主动学习相结合，以将数据采集集中在最具信息量的技能参数上。此外，ActivePusher能够与基于模型的运动动力学规划器无缝集成，利用不确定性估计来引导控制采样偏向更可靠的动作。我们在仿真和真实世界环境中评估了我们的方法，并证明与基线方法相比，它持续提高了数据效率并获得了更高的规划成功率。源代码可在 https://github.com/elpis-lab/ActivePusher 获取。