Retrospectives on the embodied ai workshop
We present a retrospective on the state of Embodied AI research. Our analysis focuses on
13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are …
13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are …
An approach to deploy interactive robotic simulators on the web for hri experiments: Results in social robot navigation
Evaluation of social robot navigation inherently requires human input due to its qualitative
nature. Motivated by the need to scale human evaluation, we propose a general method for …
nature. Motivated by the need to scale human evaluation, we propose a general method for …
Application of pretrained large language models in embodied artificial intelligence
AK Kovalev, AI Panov - Doklady Mathematics, 2022 - Springer
A feature of tasks in embodied artificial intelligence is that a query to an intelligent agent is
formulated in natural language. As a result, natural language processing methods have to …
formulated in natural language. As a result, natural language processing methods have to …
The robotic vision scene understanding challenge
Being able to explore an environment and understand the location and type of all objects
therein is important for indoor robotic platforms that must interact closely with humans …
therein is important for indoor robotic platforms that must interact closely with humans …
Evaluating the impact of semantic segmentation and pose estimation on dense semantic SLAM
Recent Semantic SLAM methods combine classical geometry-based estimation with deep
learning-based object detection or semantic segmentation. In this paper we evaluate the …
learning-based object detection or semantic segmentation. In this paper we evaluate the …
GRADE: Generating realistic animated dynamic environments for robotics research
In recent years, computer vision tasks like target tracking and human pose estimation have
immensely benefited from synthetic data generation and novel rendering techniques. On the …
immensely benefited from synthetic data generation and novel rendering techniques. On the …
BenchBot environments for active robotics (BEAR): Simulated data for active scene understanding research
We present a platform to foster research in active scene understanding, consisting of high-
fidelity simulated environments and a simple yet powerful API that controls a mobile robot in …
fidelity simulated environments and a simple yet powerful API that controls a mobile robot in …
Can visual context improve automatic speech recognition for an embodied agent?
P Pramanick, C Sarkar - arXiv preprint arXiv:2210.13189, 2022 - arxiv.org
The usage of automatic speech recognition (ASR) systems are becoming omnipresent
ranging from personal assistant to chatbots, home, and industrial automation systems, etc …
ranging from personal assistant to chatbots, home, and industrial automation systems, etc …
Improving embodied instruction following with deterministic methods
D Kim, YJ Lee - 2023 25th International Conference on …, 2023 - ieeexplore.ieee.org
We propose a modified module structure of FILM, which increases its performance on
ALFRED benchmark. Despite methods like imitation learning or reinforcement learning can …
ALFRED benchmark. Despite methods like imitation learning or reinforcement learning can …
Learning from synthetic data generated with GRADE
Recently, synthetic data generation and realistic rendering has advanced tasks like target
tracking and human pose estimation. Simulations for most robotics applications are obtained …
tracking and human pose estimation. Simulations for most robotics applications are obtained …