# Should We Learn Contact-Rich Manipulation Policies from Sampling-Based Planners?

arXiv: https://arxiv.org/abs/2412.09743 · HTML: https://mlsanity.com/paper/2412.09743/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2024.

## Built on by (most cited first, 10 of 10)

- [ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation](https://mlsanity.com/paper/2505.22159/) (2025)
- [Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization](https://mlsanity.com/paper/2502.20382/) (2025)
- [Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels](https://mlsanity.com/paper/2503.22634/) (2025)
- [Generative Predictive Control: Flow Matching Policies for Dynamic and Difficult-to-Demonstrate Tasks](https://mlsanity.com/paper/2502.13406/) (2025)
- [DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation](https://mlsanity.com/paper/2608.29078/) (2026)
- [LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains](https://mlsanity.com/paper/2503.01236/) (2025)
- [HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching](https://mlsanity.com/paper/2604.10836/) (2026)
- [FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation](https://mlsanity.com/paper/2609.03889/) (2026)
- [DATAFARM: Distribution-Aligned Task and Motion Planning for Fine-Tuning Vision-Language-Action Models](https://mlsanity.com/paper/2609.12316/) (2026)
- [Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control](https://mlsanity.com/paper/2609.34018/) (2026)

## Abstract (arXiv)

The tremendous success of behavior cloning (BC) in robotic manipulation has been largely confined to tasks where demonstrations can be effectively collected through human teleoperation. However, demonstrations for contact-rich manipulation tasks that require complex coordination of multiple contacts are difficult to collect due to the limitations of current teleoperation interfaces. We investigate how to leverage model-based planning and optimization to generate training data for contact-rich dexterous manipulation tasks. Our analysis reveals that popular sampling-based planners like rapidly exploring random tree (RRT), while efficient for motion planning, produce demonstrations with unfavorably high entropy. This motivates modifications to our data generation pipeline that prioritizes demonstration consistency while maintaining solution diversity. Combined with a diffusion-based goal-conditioned BC approach, our method enables effective policy learning and zero-shot transfer to hardware for two challenging contact-rich manipulation tasks.