Robotic Interestingness (Robotic Interestingness: A Dataset to Push the Limits of Online Visual Interesting Scene Prediction)

移动机器人视觉趣味场景预测是机器人领域最基础的研究领域之一。它对于许多机器人应用至关重要，例如机器人探索、决策和机器人协作等。因此，为移动机器人建立一种像人类一样的“视觉趣味”感非常重要。为了促进为此目的开发视觉有趣的场景预测，我们为机器人创建了这个数据集，以更好地感知世界。

Visual interesting scene prediction for mobile robots is one of the most fundamental research areas in the field of robotics. This task is vitally important for a variety of robotic applications, including robotic exploration, decision-making, and robotic collaboration. Thus, it is of paramount importance to endow mobile robots with a human-like "sense of visual interestingness". To facilitate the development of visual interesting scene prediction for this goal, we have constructed this dataset to help robots better perceive the surrounding environment.

搜集汇总

背景与挑战

背景概述

该数据集由卡内基梅隆大学于2021年发布，旨在促进移动机器人视觉趣味场景预测的研究，以增强机器人在探索、决策等应用中对世界的感知能力。