# IKFlow: Generating Diverse Inverse Kinematics Solutions

arXiv: https://arxiv.org/abs/2111.08933 · HTML: https://mlsanity.com/paper/2111.08933/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2021.

## Built on by (most cited first, 15 of 15)

- [AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing](https://mlsanity.com/paper/2207.13784/) (2022)
- [Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations](https://mlsanity.com/paper/2408.04380/) (2024)
- [SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data](https://mlsanity.com/paper/2311.02191/) (2023)
- [Inverse Kinematics for Neuro-Robotic Grasping with Humanoid Embodied Agents](https://mlsanity.com/paper/2404.08825/) (2024)
- [CycleIK: Neuro-inspired Inverse Kinematics](https://mlsanity.com/paper/2307.11554/) (2023)
- [IKDiffuser: a Diffusion-based Generative Inverse Kinematics Solver for Kinematic Trees](https://mlsanity.com/paper/2506.13087/) (2025)
- [A Design Co-Pilot for Task-Tailored Manipulators](https://mlsanity.com/paper/2509.13077/) (2025)
- [MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency](https://mlsanity.com/paper/2606.15148/) (2026)
- [PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise](https://mlsanity.com/paper/2403.08216/) (2024)
- [Application-driven Validation of Posteriors in Inverse Problems](https://mlsanity.com/paper/2309.09764/) (2023)
- [ViIK: Flow-based Vision Inverse Kinematics Solver with Fusing Collision Checking](https://mlsanity.com/paper/2408.11293/) (2024)
- [Leveraging CVAE for Joint Configuration Estimation of Multifingered Grippers from Point Cloud Data](https://mlsanity.com/paper/2511.17276/) (2025)
- [RAM: Reachability Across Morphologies](https://mlsanity.com/paper/2606.09108/) (2026)
- [Exploring the Intrinsic Geometry of Diffusion Models with Constrained Inverse Kinematics](https://mlsanity.com/paper/2606.26408/) (2026)
- [MorphIK: Morphology-Conditioned Neural Inverse Kinematics for Unknown Robots](https://mlsanity.com/paper/2609.29908/) (2026)

## Abstract (arXiv)

Inverse kinematics - finding joint poses that reach a given Cartesian-space end-effector pose - is a common operation in robotics, since goals and waypoints are typically defined in Cartesian space, but robots must be controlled in joint space. However, existing inverse kinematics solvers return a single solution pose, where systems with more than 6 degrees of freedom support infinitely many such solutions, which can be useful in the presence of constraints, pose preferences, or obstacles. We introduce a method that uses a deep neural network to learn to generate a diverse set of samples from the solution space of such kinematic chains. The resulting samples can be generated quickly (2000 solutions in under 10ms) and accurately (to within 10 millimeters and 2 degrees of an exact solution) and can be rapidly refined by classical methods if necessary.