We released "GND: Global Navigation Dataset". It is a large-scale dataset from 5 college campuses, and lthat integrates multi-modal sensory data, including 3D LiDAR point clouds, RGB images, and 360° images, along with multi-category traversability maps.
https://t.co/i8HLlxHotd
Thank you so much @TheRegister, for covering our recent work on the "#Safety Concerns of Deploying #GenerativeAI AI in #Robotics"
Link to Thread: https://t.co/qp08XXb5ct
🚀🤖Integration of #LLMs & #VLMs into #Robotics is redefining what robots can do! 🚨But it raises questions on #AISafety, #Reliability, & #Robustness. 💡Our latest work shows that it might be vulnerable to simple adversarial attacks.
Check it out ➡️ [https://t.co/ok5FAwqLUN]
⚠️ Safety Alert! ⚠️
🔥As we embrace the incredible advancements in robotics powered by #GenerativeAI, like #LLMs and #VLMs, a critical question emerges:
☠️Is it Safe and Reliable to deploy LLM/VLMs in Robotics❓
#RoboticsSafety#AISafety#DataSecurity
See you Saturday 17:15-19:17 at Naupaka #51 #WACV2024
For aerial videos, we proposed MITFAS to focus on the regions corresponding to salient motions and find the more informative frames by using mutual information.
@RuiqiXian@dmanocha@gammaumd
Join us at Naupaka #74, Saturday 17:15-19:15! #WACV2024
We proposed PMI Sampler for aerial footage, it efficiently selects key frames using patch-wise mutual information. Ideal for moving camera footage with dynamic backgrounds.
@xijunwang_cs @DivyaKRaman1 @dmanocha@gammaumd