R900: Understanding the Cost-Effectiveness of Random Exploration from 900 Hours of Robotic Data Collection

Data scarcity presents a key bottleneck for imitation learning in robotic manipulation. In this paper, we focus on random exploration data-actions and video sequences produced autonomously via motions to randomly sampled positions in the workspace-to investigate their potential as a cost-effective data source. Our investigation follows two paradigms: (a) random actions, where we assess their feasibility for autonomously bootstrapping data collection policies, and (b) random exploration video frames, where we evaluate their effectiveness in pre-training parameter-dense networks with self-supervised learning objectives. To minimize human supervision, we first develop a fully automated pipeline that handles episode labeling, termination, and resetting using cloud-based microservices for real-time monitoring. Building on this, we present a large-scale study on the cost-effectiveness of real-world random exploration in a non-trivial two-layer stacking task, drawing on statistical results from 807 hours of random actions, 71 hours of random exploration video (1.28M frames), and 1,260 times of policy evaluation. The dataset will be made publicly available and access to the robot environment with the automated pipeline is to be made accessible via cloud service for future research.