We propose to learn to generate grasping motion for manipulation with a dexterous hand using implicit functions. With continuous time inputs, the model can generate a continuous and smooth grasping plan. We name the proposed model Continuous Grasping Function (CGF). CGF is learned via generative modeling with a Conditional Variational Autoencoder using 3D human demonstrations. We will first convert the large-scale human-object interaction trajectories to robot demonstrations via motion retargeting, and then use these demonstrations to train CGF. During inference, we perform sampling with CGF to generate different grasping plans in the simulator and select the successful ones to transfer to the real robot. By training on diverse human data, our CGF allows generalization to manipulate multiple objects. Compared to previous planning algorithms, CGF is more efficient and achieves significant improvement on success rate when transferred to grasping with the real Allegro Hand. Our project page is available at https://jianglongye.com/cgf .

翻译：我们提出一种利用隐式函数生成灵巧手操作抓取运动的方法。通过连续时间输入，该模型可生成连续平滑的抓取规划。我们将所提模型命名为连续抓取函数（CGF）。CGF通过条件变分自编码器基于3D人类演示进行生成式建模学习。我们首先通过运动重定向将大规模人-物交互轨迹转换为机器人演示，再基于这些演示训练CGF。推理阶段，我们通过CGF采样在仿真器中生成不同抓取规划，选取成功案例迁移至真实机器人。通过多样化人类数据训练，CGF具备泛化操作多个物体的能力。相较于现有规划算法，CGF在迁移至真实Allegro Hand抓取时效率更高，成功率显著提升。项目主页参见https://jianglongye.com/cgf。