Retrospectives on the Embodied AI Workshop

Matt, Deitke,; Batra, Dhruv; Bisk, Yonatan; Campari, Tommaso; Chang, Angel X.; Chaplot, Devendra Singh; Chen, Changan; D'Arpino, Claudia Pérez; Ehsani, Kiana; Farhadi, Ali; Li, Feifei; Francis, Anthony; Gan, Chuang; Grauman, Kristen; Hall, D.; Han, Winson; Jain, Unnat; Kembhavi, Aniruddha; Krantz, Jacob; Lee, Stefan; Li, Chengshu; Majumder, Sagnik; Maksymets, Oleksandr; Roberto, Martín-Martín,; Mottaghi, Roozbeh; Raychaudhuri, Sonia; Roberts, Michael J.; Savarese, Silvio; Savva, Manolis; Shridhar, M.H; Sünderhauf, Niko; Szot, Andrew; Talbot, Ben; Tenenbaum, Joshua B.; Thomason, Jesse; Toshev, Alexander; Truong, Joanne; Weihs, Luca

doi:10.48550/arxiv.2210.06849

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive experiments demonstrate the effectiveness of the proposed method, and our system achieves state-of-theart on two VLN-CE benchmarks (e.g., in test unseen splits, 55% SR and 48% SPL on R2R-CE dataset, 51.21% SR and 41.30% SDTW on RxR-CE dataset). Based on the algorithm described in this paper, we won the CVPR 2022 RxR-Habitat Challenge [11], [18]. In summary, the contributions of this work are four-fold:…”

Section: Introductionmentioning

confidence: 99%

Structured Scene Memory for Vision-Language Navigation

Wang

Yang

Liang

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. It becomes increasingly crucial in the field of embodied AI, with potential applications in autonomous navigation, search and rescue, and human-robot interaction. In this paper, we propose to address a more practical yet challenging counterpart setting -vision-language navigation in continuous environments (VLN-CE). To develop a robust VLN-CE agent, we propose a new navigation framework, ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments. ETPNav performs online topological mapping of environments by self-organizing predicted waypoints along a traversed path, without prior environmental experience. It privileges the agent to break down the navigation procedure into high-level planning and low-level control. Concurrently, ETPNav utilizes a transformer-based cross-modal planner to generate navigation plans based on topological maps and instructions. The plan is then performed through an obstacle-avoiding controller that leverages a trial-and-error heuristic to prevent navigation from getting stuck in obstacles. Experimental results demonstrate the effectiveness of the proposed method. ETPNav yields more than 10% and 20% improvements over prior state-of-the-art on R2R-CE and RxR-CE datasets, respectively. Our code is available at https://github.com/MarSaKi/ETPNav.

show abstract

Section: Introductionmentioning

confidence: 99%

Structured Scene Memory for Vision-Language Navigation

Wang

Yang

Liang

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Recent advances in large language models (LLMs) have led some people to believe that LLMs alone can eventually give rise to AGI -Artificial General Intelligence (Bubeck et al 2023;Michael et al 2022;Zhang et al 2023). On the contrary, this short position essay argues the opposite -that AGI not only requires embodiment (Deitke et al 2022;Duan et al 2022b), but that in the absence of a widely-accepted "acid test" for AGI, embodied intelligence is the key towards convincing demonstrations of AGI.…”

Section: Introductionmentioning

confidence: 91%

The Path to AGI Goes through Embodiment

Tan,

Jaiswal

2023

AAAI-SS

View full text Add to dashboard Cite

Recent advances in large language models have raised the question of whether these language models alone could lead to artificial general intelligence (AGI). In this short position essay, we argue that embodiment is not only required for achieving AGI, but also that embodiment is the key to convincingly demonstrate AGI capabilities. There is no single widely-accepted, objective test for AGI, so therefore whether a system has achieved AGI is a subjective judgement. We argue that a language-only system or one that cannot demonstrate success in the real world would not be convincing.

show abstract

Retrospectives on the Embodied AI Workshop

Cited by 2 publications

References 0 publications

Structured Scene Memory for Vision-Language Navigation

Structured Scene Memory for Vision-Language Navigation

The Path to AGI Goes through Embodiment

Contact Info

Product

Resources

About