Most learned dexterous grasp generators relegate contact forces to a downstream verification step, so a kinematically-plausible pose can still violate the conditions for a stable physical grasp. We address this with EquiDexFlow, an SE(3)-equivariant flow-matching model that jointly predicts wrist pose, joint angles, fingertip contacts, surface normals, and contact forces from an object point cloud. Our architecture projects contacts onto the object surface and forces into the Coulomb friction cone by construction, so placement and friction compliance hold without loss penalties. We prove end-to-end SE(3) equivariance and verify it empirically over 200 rotations, with wrist residuals below $0.04^\circ$ and exactly zero joint deviation. Trained on 8,100 force-closure grasps across 81 objects for the 16-DoF Allegro Hand, our model achieves zero friction violations, the best composite score, and the lowest wrench residual among all ablation variants. We retarget decoded fingertip contacts to a 16-DoF LEAP Hand via per-finger inverse kinematics, and our hardware-feasible refinement places every joint at least 5% inside its actuator envelope while preserving wrench balance. On the physical robot, retargeted EquiDexFlow-decoded grasps complete open-loop pick-and-hold trials on all six test objects, with every asymmetric object succeeding at both the canonical pose and a $120^\circ$ co-rotation. Videos, code, and checkpoints are available at https://equidexflow.github.io.

翻译：[摘要译] 现有的大多数习得型灵巧抓取生成器将接触力作为下游验证步骤，导致运动学上可行的抓取姿态仍可能违反稳定物理抓取的条件。为此，我们提出EquiDexFlow——一个SE(3)等变流匹配模型，可从物体点云联合预测手腕位姿、关节角、指尖接触点、表面法向及接触力。通过结构设计将接触点投影至物体表面并将力约束至库仑摩擦锥内，使接触放置与摩擦顺应性无需损失惩罚项即可自动满足。我们证明了端到端的SE(3)等变性，并在200次旋转测试中通过实验验证：手腕残差低于0.04°，关节偏差严格为零。该模型基于16自由度Allegro机械手在81个物体的8,100个力闭合抓取上训练，在所有消融变体中实现了零摩擦违反、最高综合评分及最低力螺旋残差。通过单指逆运动学将解码的指尖接触点重定位至16自由度LEAP机械手，硬件可行的优化方案使每个关节在执行器包络内至少保留5%余量，同时保持力螺旋平衡。在实体机器人上，重定位的EquiDexFlow解码抓取对全部六个测试物体完成开环抓取-保持实验，每个非对称物体在标准姿态与120°共旋转姿态下均成功。视频、代码及模型权重已开源至https://equidexflow.github.io。