David Suter, Muraleekrishna Gopinathan, Martin Masek, Jumana Abu-Khalaf
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Embodied AI aims to develop robots that can understand and execute human language instructions, as well as communicate in natural languages. On this front, we study the task of generating highly detailed navigational instructions for the embodied robots to follow. Although recent studies have demonstrated significant leaps in the generation of step-by-step instructions from sequences of images, the generated instructions lack variety in terms of their referral to objects and landmarks. Existing speaker models learn strategies to evade the evaluation metrics and obtain higher scores even for low-quality sentences. In this work, we propose SAS (Spatially-Aware Speaker), an instruction generator or Speaker model that utilises both structural and semantic knowledge of the environment to produce richer instructions. For training, we employ a reward learning method in an adversarial setting to avoid systematic bias introduced by language evaluation metrics. Empirically, our method outperforms existing instruction generation models, evaluated using standard metrics. Our code is available at https://github. com/gmuraleekrishna/SAS.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.05583")
get_code_for_paper("2409.05583")
have("2409.05583")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.05583.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.05583)
Connect an agent — have() is free.