# A Structured Prediction Approach for Robot Imitation Learning

arXiv: https://arxiv.org/abs/2309.14829 · HTML: https://mlsanity.com/paper/2309.14829/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 23 of its 74 references that are in the map.
- First posted on arXiv 26 Sep 2023.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 23 of 23)

- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [Imitation Learning as f-Divergence Minimization](https://mlsanity.com/paper/1905.12888/) (2019)
- [Less is More: Nystr"om Computational Regularization](https://mlsanity.com/paper/1507.04717/) (2015)
- [Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap](https://mlsanity.com/paper/2103.03236/) (2021)
- [Neural Dynamic Policies for End-to-End Sensorimotor Learning](https://mlsanity.com/paper/2012.02788/) (2020)
- [Kernelized Movement Primitives](https://mlsanity.com/paper/1708.08638/) (2017)
- [A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings](https://mlsanity.com/paper/2002.05424/) (2020)
- [Teleoperation of Humanoid Robots: A Survey](https://mlsanity.com/paper/2301.04317/) (2023)
- [A Consistent Regularization Approach for Structured Prediction](https://mlsanity.com/paper/1605.07588/) (2016)
- [Fast Policy Learning through Imitation and Reinforcement](https://mlsanity.com/paper/1805.10413/) (2018)
- [Learning Riemannian Manifolds for Geodesic Motion Skills](https://mlsanity.com/paper/2106.04315/) (2021)
- [Gaussians on Riemannian Manifolds: Applications for Robot Learning and Adaptive Control](https://mlsanity.com/paper/1909.05946/) (2019)
- [Identification of Fully Physical Consistent Inertial Parameters using Optimization on Manifolds](https://mlsanity.com/paper/1610.08703/) (2016)
- [Efficient Path Planning in Narrow Passages for Robots with Ellipsoidal Components](https://mlsanity.com/paper/2104.04658/) (2021)
- [Manifold Structured Prediction](https://mlsanity.com/paper/1806.09908/) (2018)
- [Trajectory Optimization on Manifolds: A Theoretically-Guaranteed Embedded Sequential Convex Programming Approach](https://mlsanity.com/paper/1905.07654/) (2019)
- [Task-Adaptive Robot Learning from Demonstration with Gaussian Process Models under Replication](https://mlsanity.com/paper/2010.07795/) (2020)
- [Ultrasound-Guided Assistive Robots for Scoliosis Assessment with Optimization-based Control and Variable Impedance](https://mlsanity.com/paper/2203.02126/) (2022)

## Built on by (most cited first, 1 of 1)

- [FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths](https://mlsanity.com/paper/2511.01407/) (2025)

## Abstract (arXiv)

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework.