Robots Calling the Shots: Using Multiple Ground Robots for Autonomous Tracking in Cluttered Environments

Abstract

A common task in cinematography is tracking a subject or character through a scene. For complex setups, multiple cameras must track the subject simultaneously to attain sufficient coverage. Recently, researchers have considered using multiple camera-mounted autonomous mobile robots for this task. Existing work is limited to UAVs, which may be unavailable due to cost, safety requirements, or flight restrictions. Therefore, in this paper we present a tracking approach for complex and unstructured environments using differential-drive robots with gimbal-mounted cameras. Differential-Drive robots pose a challenge, as their movement is more restricted than UAVs. For this, we introduce a novel hierarchical planning framework which ensures safety and visibility while maximizing shot diversity. We begin by synthesizing a set of paths using sequential greedy viewpoint planning and conflict-based search under a set of optimal viewpoint constraints. These paths then form an initial guess for joint trajectory optimization, which synthesizes stable trajectories under the motion constraints of the robots and gimbals. Empirically, we show how our approach outperforms approaches aimed at UAVs, which may synthesize infeasible trajectories when applied to differential-drive robots.