# HarvestFlex: Strawberry Harvesting via Vision-Language-Action Policy Adaptation in the Wild

arXiv: https://arxiv.org/abs/2603.05982 · HTML: https://mlsanity.com/paper/2603.05982/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [Igniting VLMs toward the Embodied Space](https://mlsanity.com/paper/2509.11766/) (2025)
- [VLMPC: Vision-Language Model Predictive Control for Robotic Manipulation](https://mlsanity.com/paper/2407.09829/) (2024)
- [AgriGPT-VL: Agricultural Vision-Language Understanding Suite](https://mlsanity.com/paper/2510.04002/) (2025)
- [Towards Autonomous Selective Harvesting: A Review of Robot Perception, Robot Design, Motion Planning and Control](https://mlsanity.com/paper/2304.09617/) (2023)
- [Design and Control of a Novel Six-Degree-of-Freedom Hybrid Robotic Arm](https://mlsanity.com/paper/2407.19826/) (2024)
- [Vision-Based Early Fault Diagnosis and Self-Recovery for Strawberry Harvesting Robots](https://mlsanity.com/paper/2601.02085/) (2026)

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

- [Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review](https://mlsanity.com/paper/2607.06706/) (2026)

## Abstract (arXiv)

This work presents the first study on transferring vision-language-action (VLA) policies to real greenhouse tabletop strawberry harvesting, a long-horizon, unstructured task challenged by occlusion and specular reflections. We built an end-to-end closed-loop system on the HarvestFlex platform using three-view RGB sensing (two fixed scene views plus a wrist-mounted view) and intentionally avoided depth clouds and explicit geometric calibration. We collected 3.71 h of VR teleoperated demonstrations (227 episodes) and fine-tuned pi_0, pi_0.5, and WALL-OSS with full fine-tuning and LoRA. Under a unified 50 trials real-greenhouse protocol and metrics spanning completion, pi_0.5 with full fine-tuning achieved success rate of 74.0% with 32.6 s/pick and damage rate of 4.1%. Asynchronous inference-control decoupling further improved performance over synchronous deployment. Results showed non-trivial closed-loop picking with fewer than four hours of real data, while remaining limited by close-range observability loss and contact-dynamics mismatch. A demonstration video is available at: https://youtu.be/bN8ZowZKPMI.