Focus on Impact: Indoor Exploration With Intrinsic Motivation

Bigazzi, Roberto; Landi, Federico; Cascianelli, Silvia; Baraldi, Lorenzo; Cornia, Marcella; Cucchiara, Rita

doi:10.1109/lra.2022.3145971

Cited by 17 publications

(8 citation statements)

References 54 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We provide an experimental analysis comparing recently proposed approaches on the devised environment, both for exploration and PointNav++ tasks. The evaluated methods are consistent with recent literature on embodied AI [10,20,5] and adopt an architecture shown in Fig. 3, which is composed of a neural mapper, a pose estimator, and a hierarchical navigation policy.…”

Section: Architecturesupporting

confidence: 57%

“…Both autonomous robotics [5,14] and embodied AI [8,11,18,6,12,21] have recently witnessed a boost of interest, which has been enabled by the release of photorealistic 3D simulated environments. In such environments, algorithms for intelligent exploration and navigation can be developed safely and more quickly than in the real-world, before being easily deployed on real robotic platforms [15,7,2].…”

Section: Related Workmentioning

confidence: 99%

“…Current agents for embodied exploration feature a modular approach [5,10,20]. While the agents are trained for embodied exploration using deep reinforcement learning, this hierarchical paradigm allows for great adaptability on downstream tasks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Embodied Navigation at the Art Gallery

Bigazzi¹,

Landi²,

Cascianelli³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Embodied agents, trained to explore and navigate indoor photorealistic environments, have achieved impressive results on standard datasets and benchmarks. So far, experiments and evaluations have involved domestic and working scenes like offices, flats, and houses. In this paper, we build and release a new 3D space with unique characteristics: the one of a complete art museum. We name this environment ArtGallery3D (AG3D). Compared with existing 3D scenes, the collected space is ampler, richer in visual features, and provides very sparse occupancy information. This feature is challenging for occupancy-based agents which are usually trained in crowded domestic environments with plenty of occupancy information. Additionally, we annotate the coordinates of the main points of interest inside the museum, such as paintings, statues, and other items. Thanks to this manual process, we deliver a new benchmark for PointGoal navigation inside this new space. Trajectories in this dataset are far more complex and lengthy than existing groundtruth paths for navigation in Gibson and Matterport3D. We carry on extensive experimental evaluation using our new space for evaluation and prove that existing methods hardly adapt to this scenario. As such, we believe that the availability of this 3D model will foster future research and help improve existing solutions.

show abstract

Section: Architecturesupporting

confidence: 57%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Embodied Navigation at the Art Gallery

Bigazzi¹,

Landi²,

Cascianelli³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…More recently, inspired by the exploration-exploitation trade-off and intelligent exploration [3] [4] [5] [6] in reinforcement learning (RL), RL based approaches were used on robot exploration [7] [8]. In these methods, the value functions are learned from the experience sampled from the online interactions with the environment.…”

Section: Introductionmentioning

confidence: 99%

Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments

Hu¹,

Wang²,

Keller³

et al. 2022

Preprint

View full text Add to dashboard Cite

In traditional robot exploration methods, the robot usually does not have prior biases about the environment it is exploring. Thus the robot assigns equal importance to the goals which leads to insufficient exploration efficiency. Alternative, often a hand-tuned policy is used to tweak the value of goals. In this paper, we present a method to learn how "good" some states are, measured by the state value function, to provide a hint for the robot to make exploration decisions. We propose to learn state value functions from previous offline collected datasets and then transfer and improve the value function during testing in a new environment. Moreover, the environments usually have very few and even no extrinsic reward or feedback for the robot. Therefore in this work, we also tackle the problem of sparse extrinsic rewards from the environments. We design several intrinsic rewards to encourage the robot to obtain more information during exploration. These reward functions then become the building blocks of the state value functions. We test our method on challenging subterranean and urban environments. To the best of our knowledge, this work for the first time demonstrates value function prediction with previous collected datasets to help exploration in challenging subterranean environments.

show abstract

“…After the robot knows your house, instead, you expect it to perform navigation tasks much faster, exploiting its previous knowledge of the environment while adapting to possible changes of objects, people, and furniture positioning. Embodied AI has recently gained a lot of attention from the research community, with amazing results in challenging tasks such as visual exploration [1], [2], [3] and navigation [4], [5], [6], [7]. However, in the current setting, the environment is completely unknown to the agent as a new episode begins.…”

Section: Introductionmentioning

confidence: 99%

Spot the Difference: A Novel Task for Embodied Agents in Changing Environments

Landi¹,

Bigazzi²,

Cornia³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Embodied AI is a recent research area that aims at creating intelligent agents that can move and operate inside an environment. Existing approaches in this field demand the agents to act in completely new and unexplored scenes. However, this setting is far from realistic use cases that instead require executing multiple tasks in the same environment. Even if the environment changes over time, the agent could still count on its global knowledge about the scene while trying to adapt its internal representation to the current state of the environment. To make a step towards this setting, we propose Spot the Difference: a novel task for Embodied AI where the agent has access to an outdated map of the environment and needs to recover the correct layout in a fixed time budget. To this end, we collect a new dataset of occupancy maps starting from existing datasets of 3D spaces and generating a number of possible layouts for a single environment. This dataset can be employed in the popular Habitat simulator and is fully compliant with existing methods that employ reconstructed occupancy maps during navigation. Furthermore, we propose an exploration policy that can take advantage of previous knowledge of the environment and identify changes in the scene faster and more effectively than existing agents. Experimental results show that the proposed architecture outperforms existing state-of-the-art models for exploration on this new setting.

show abstract

Focus on Impact: Indoor Exploration With Intrinsic Motivation

Cited by 17 publications

References 54 publications

Embodied Navigation at the Art Gallery

Embodied Navigation at the Art Gallery

Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments

Spot the Difference: A Novel Task for Embodied Agents in Changing Environments

Contact Info

Product

Resources

About