@oksenlisovyi Пане @oksenlisovyi чому це не регулювати ліцензіями НАЗЯВО? І хто взагалі акредитував програми, які, як Ви згадуєте, набирають сотні/тисячі студентів? Чому не змінювати правил тут і не виводити на чисту воду осіб, які це роблять? Як бути приватним університетам?
Presenting our EmbodiedAI Workshop paper in collaboration with @UCU_Faculty_of_APPS and @rpartsey "What Do We Learn from Using Text Captions as a Form of 3D Scene Representation?" poster 76 ARCH 4E at #CVPR2024 from 1pm to 2pm today.
Today we’re announcing Habitat 3.0, Habitat Synthetic Scenes Dataset and HomeRobot — three major advancements in the development of social embodied AI agents that can cooperate with and assist humans in daily tasks.
More details on these announcements ➡️ https://t.co/WGSjkkyQx3
The future of robot butlers starts with mobile manipulation.
We’re announcing the NeurIPS 2023 Open-Vocabulary Mobile Manipulation Challenge!
- Full robot stack ✅
- Parallel sim and real evaluation ✅
- No robot required ✅👀
https://t.co/mggAbRhrLP
@MetaAI Btw, @MetaAI, the application form of the Montreal location is not behaving as expected on the 4th step. Field description asks to submit two-page PDF document but, in fact, the field is of type text not file upload.
Habitat stable version v0.2.3 released!
— New Algorithm: Variable Experience Rollout
https://t.co/WAG6NEKda1
— New Task: Instance ImageGoal Navigation https://t.co/tQFQVBVtJ0
— New config system: Hydra
— New robots: @hellorobotinc Stretch, @BostonDynamics Spot
and more ...
Even though this is not the first release I contributed to. But it is special for me as I was co-migrating Habitat’s configuration system to Hydra (that’s one of the biggest enhancements).
Paper Club with the author of the paper, what could be better?
Let's meet to discuss the new paper and answer the question: Is Mapping Necessary for Realistic PointGoal Navigation?
Lecturer and research author — @rpartsey.
⚡️Register at https://t.co/OHGpdZmWRz
In zero-shot sim2real experiments, the agent does well at avoiding obstacles, but the most challenging part seems to be stopping within the success threshold. Across 9 episodes, it achieves 11% Success, 65% SoftSPL, and makes it 92% of the way to the goal (SoftSuccess).
Is Mapping Necessary for Realistic PointGoal Navigation?
@rpartsey, @erikwijmans, @naokiyokoyama0, @dobosevych , @DhruvBatraDB ,@o_maksymets
tl;dr: learned odometry + learned navigation w/o mapping seems to work well enough among single dataset.
https://t.co/liV5RdVbIP
Trained on Gibson train split, our agent follows a near-perfect path on both Gibson and MP3D val scenes. It scores 96% Success, 77% SPL, 76% SoftSPL on Gibson and 79% Success, 60% SPL, 69% SoftSPL on Matterport3D.