An Exploration of Embodied Visual Exploration

Abstract

Embodied computer vision considers perception for robots in novel, unstructured environments. Of particular importance is the embodied visual exploration problem: how might a robot equipped with a camera scope out a new environment? Despite the progress thus far, many basic questions pertinent to this problem remain unanswered: (i) What does it mean for an agent to explore its environment well? (ii) Which methods work well, and under which assumptions and environmental settings? (iii) Where do current approaches fall short, and where might future work seek to improve? Seeking answers to these questions, we first present a taxonomy for existing visual exploration algorithms and create a standard framework for benchmarking them. We then perform a thorough empirical study of the four state-of-the-art paradigms using the proposed framework with two photorealistic simulated 3D environments, a state-of-the-art exploration architecture, and diverse evaluation metrics. Our experimental results offer insights and suggest new performance metrics and baselines for future work in visual exploration. Code, models and data are publicly available.

Focus on Impact: Indoor Exploration with Intrinsic Motivation

“…These methods have been largely used and improved [24], [25], [17] or combined in a hierarchical exploration algorithm [16], [2]. However, when applied with noisy odometry and localization sensors or in highly complex environments, geometric approaches tend to fail [8], [17], [18]. In light of this, increasing research effort has been dedicated to the development of learning-based approaches, which usually exploit DLR to learn robust and efficient exploration policies.…”

“…In the context of robotic exploration and navigation tasks, the introduction of photorealistic simulators has represented a breeding ground for the development of self-supervised DRLbased visual exploration methods. Ramakrishnan et al [18] identified four paradigms for visual exploration: novelty-based, curiosity-based (as defined above), reconstruction-based, and coverage-based. Each paradigm is characterized by a different reward function used as a self-supervision signal for optimizing the exploration policy.…”

“…Most of the recently devised exploration algorithms exploit deep reinforcement learning (DRL) [16], as learning-based exploration and navigation algorithms are more flexible and robust to noise than geometric methods [8], [17], [18]. Despite these advantages, one of the main challenges in training DRLbased exploration algorithms is designing appropriate rewards.…”

“…To overcome these issues, a different line of work focuses on the design of intrinsic reward functions, that can be computed by the agent by means of their current and past observations. Some examples of recently proposed intrinsic rewards for robot exploration are based on curiosity [21], novelty [18], and coverage [7]. All these rewards, however, tend to vanish with the length of the episode because the agent quickly learns to model the environment dynamics and appearance (for curiosity and novelty-based rewards) or tends to stay in previously-explored areas (for the coverage reward).…”

Guest Editorial: Special Issue on Performance Evaluation in Computer Vision

“…Several papers contribute novel metrics and taxonomies for the evaluation of different tasks, including multi-object tracking (Luiten et al 2021), semantic segmentation (Yan et al 2021), visual place recognition (Zaffar et al 2021), image quality assessment (Ding et al 2021), conditional image generation (Benny et al 2021), and embodied exploration (Ramakrishnan et al 2021).…”