# Learning to Pick at Non-Zero-Velocity from Interactive Demonstrations

arXiv: https://arxiv.org/abs/2110.04534 · HTML: https://mlsanity.com/paper/2110.04534/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 9 Oct 2021.

## Builds on (most cited first, 3 of 3)

- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Learning Variable Impedance Control for Contact Sensitive Tasks](https://mlsanity.com/paper/1907.07500/) (2019)
- [ILoSA: Interactive Learning of Stiffness and Attractors](https://mlsanity.com/paper/2103.03099/) (2021)

## Built on by (most cited first, 6 of 6)

- [Interactive Imitation Learning of Bimanual Movement Primitives](https://mlsanity.com/paper/2210.16220/) (2022)
- [Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Robotics](https://mlsanity.com/paper/2308.05483/) (2023)
- [Interactive incremental learning of generalizable skills with local trajectory modulation](https://mlsanity.com/paper/2409.05655/) (2024)
- [Anticipatory Planning: Improving Long-Lived Planning by Estimating Expected Cost of Future Tasks](https://mlsanity.com/paper/2305.04692/) (2023)
- [E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories](https://mlsanity.com/paper/2210.07887/) (2022)
- [A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learning](https://mlsanity.com/paper/2410.24035/) (2024)

## Abstract (arXiv)

This work investigates how the intricate task of a continuous pick & place (P&P) motion may be learned from humans based on demonstrations and corrections. Due to the complexity of the task, these demonstrations are often slow and even slightly flawed, particularly at moments when multiple aspects (i.e., end-effector movement, orientation, and gripper width) have to be demonstrated at once. Rather than training a person to give better demonstrations, non-expert users are provided with the ability to interactively modify the dynamics of their initial demonstration through teleoperated corrective feedback. This in turn allows them to teach motions outside of their own physical capabilities. In the end, the goal is to obtain a faster but reliable execution of the task. The presented framework learns the desired movement dynamics based on the current Cartesian position with Gaussian Processes (GPs), resulting in a reactive, time-invariant policy. Using GPs also allows online interactive corrections and active disturbance rejection through epistemic uncertainty minimization. The experimental evaluation of the framework is carried out on a Franka-Emika Panda. Tests were performed to determine i) the framework's effectiveness in successfully learning how to quickly pick & place an object, ii) ease of policy correction to environmental changes (i.e., different object sizes and mass), and iii) the framework's usability for non-expert users.