Berkeley, California, United States
Contact Info
19K followers
500+ connections
Articles by Aparna
Activity
-
I am thrilled to receive the IEEE Kiyo Tomiyasu Award for outstanding early to mid-career contributions to technologies holding the promise of…
I am thrilled to receive the IEEE Kiyo Tomiyasu Award for outstanding early to mid-career contributions to technologies holding the promise of…
Liked by Aparna Dhinakaran
-
Speaking at Observe: Jocelyn Z. M. (Pinecone) on building remarkable GenAI applications fast. Next week we'll hear more about what’s possible in…
Speaking at Observe: Jocelyn Z. M. (Pinecone) on building remarkable GenAI applications fast. Next week we'll hear more about what’s possible in…
Liked by Aparna Dhinakaran
-
Next week: Want to make models 10x faster and better? Dmytro Dzhulgakov (Co-Founder, Fireworks AI) will cover modern app innovation at Arize:Observe.…
Next week: Want to make models 10x faster and better? Dmytro Dzhulgakov (Co-Founder, Fireworks AI) will cover modern app innovation at Arize:Observe.…
Liked by Aparna Dhinakaran
Experience & Education
Publications
-
A Hybrid Framework for Multi-Vehicle Collision Avoidance
IEEE Conference on Decision and Control
With the recent surge of interest in UAVs for civilian services, the importance of developing tractable multi-agent analysis techniques that provide safety and performance guarantees have drastically increased. Hamilton-Jacobi (HJ) reachability has successfully provided these guarantees to small-scale systems and is flexible in terms of system dynamics. However, the exponential complexity scaling of HJ reachability with respect to system dimension prevents its direct application to larger-scale…
With the recent surge of interest in UAVs for civilian services, the importance of developing tractable multi-agent analysis techniques that provide safety and performance guarantees have drastically increased. Hamilton-Jacobi (HJ) reachability has successfully provided these guarantees to small-scale systems and is flexible in terms of system dynamics. However, the exponential complexity scaling of HJ reachability with respect to system dimension prevents its direct application to larger-scale problems where the number of vehicles is greater than two. In this paper, we propose a collision avoidance algorithm using a hybrid framework for N+1 vehicles through higher-level control logic given any N-vehicle collision avoidance algorithm. Our algorithm conservatively approximates a guaranteed-safe region in the joint state space of the N+1 vehicles and produces a safety-preserving controller. In addition, our algorithm does not incur significant additional computation cost. We demonstrate our proposed method in simulation.
-
Affordable and personalized lighting using inverse modeling and virtual sensors
SPIE - International Society for Optics and Photonics
Languages
-
English
Native or bilingual proficiency
-
Tamil
Native or bilingual proficiency
-
Spanish
Limited working proficiency
Organizations
-
Girls Who Code
Mentor
- -
UC Berkeley Lightweight Crew
-
-
More activity by Aparna
-
I am excited to share that Arize-Phoenix-Evals v0.13.0 now includes a new SQLEvaluator for evaluating SQL queries generated by LLMs. Additionally…
I am excited to share that Arize-Phoenix-Evals v0.13.0 now includes a new SQLEvaluator for evaluating SQL queries generated by LLMs. Additionally…
Liked by Aparna Dhinakaran
-
The MLOps Playbook Series: Meet Claire L.! 👋 In our new series, we explore the insights and experiences of industry leaders shaping Machine…
The MLOps Playbook Series: Meet Claire L.! 👋 In our new series, we explore the insights and experiences of industry leaders shaping Machine…
Liked by Aparna Dhinakaran
-
📣 New blog: Guardrails logs are OTEL-compliant, so you can use Guardrails with your existing observability tools to get very detailed information…
📣 New blog: Guardrails logs are OTEL-compliant, so you can use Guardrails with your existing observability tools to get very detailed information…
Liked by Aparna Dhinakaran
-
I had way too much confidence in myself to organize an in-person conf. I did a few virtual conferences and in-person meetups. It couldn't be much…
I had way too much confidence in myself to organize an in-person conf. I did a few virtual conferences and in-person meetups. It couldn't be much…
Liked by Aparna Dhinakaran
-
I'm currently in San Francisco for the AI Engineer World's Fair. I'll give a talk tomorrow at 2:40 PM about everything you need to know about…
I'm currently in San Francisco for the AI Engineer World's Fair. I'll give a talk tomorrow at 2:40 PM about everything you need to know about…
Liked by Aparna Dhinakaran
-
📰 WANTED: AI observability & LLM evaluation pioneer seeking a developer-savvy product marketer. Must speak fluent Python, conversational JS…
📰 WANTED: AI observability & LLM evaluation pioneer seeking a developer-savvy product marketer. Must speak fluent Python, conversational JS…
Liked by Aparna Dhinakaran
-
🚀 We're Hiring! Join Our AI Team at Clearcover! 🚀 Are you passionate about machine learning and generative AI? Do you want to work in an innovative…
🚀 We're Hiring! Join Our AI Team at Clearcover! 🚀 Are you passionate about machine learning and generative AI? Do you want to work in an innovative…
Liked by Aparna Dhinakaran
-
Amazing opportunity to demo to the AI community at Observe in SF next month. Applications for the Builders Lounge close June 30. 👇
Amazing opportunity to demo to the AI community at Observe in SF next month. Applications for the Builders Lounge close June 30. 👇
Shared by Aparna Dhinakaran
-
Thrilled to have been part of GopherCon Europe in Berlin! Really wonderful set of attendees and speakers, thanks so much to Natalie Pistunovich and…
Thrilled to have been part of GopherCon Europe in Berlin! Really wonderful set of attendees and speakers, thanks so much to Natalie Pistunovich and…
Liked by Aparna Dhinakaran
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More