-
Agentic LLM for Parametertic CAD model TOP NEW
Does it work? Thought this would be the most insightful to those interested, Yes it does work but in a very limited capacity, using LLMs to generate CAD models with more than 3-5 parts with geometry closer to simple forms like square, rectangular, spherical did work for me. However, even at that I had issue staying consistent with OpenAI O1 or G... Read More
-
Detection of micro object in 3D space using SPAD sensor TOP NEW
Introduction There are two type of photon detection system one is conventional LiDAR probably most familiar to us because of its wide use in robotics, autonomous driving vehicles and many other ranging technology. The other type is less researched and not as widely used - single photon avalanche diaode(SPAD) sensor. SPAD sensor is used for simil... Read More
-
Breakaway From the Conventional Roof System TOP NEW
So what are Bóvedas anyway? Bóvedas is Spanish for Vaults, used to cover spaces with curved surfaces forming the roof or ceiling of a structure. The most famous example of a Bóvedas is Duomo in Florence, Italy. The structure when build may or may not use forms underneath it, and once built it can be danced upon with a tune of your favorite EDM ... Read More
-
Building a Solar Powered Car TOP NEW
Building a solar powered car is a challenging project that requires a team of dedicated individuals to come together and work towards a common goal. The ETROS team at SRM Chennai is one such team that has been working towards building a solar powered car for the Solar Car Challenge since 2015. Read More
-
Forward and Inverse Kinematics on Dobot Magician Lite TOP NEW
This post documents a compact pipeline to compute forward kinematics (FK) and inverse kinematics (IK) for the Dobot Magician Lite, and to execute accurate pick-and-place motions. Robot: Dobot Magician Lite (3-DOF arm + end-effector) Goal: Convert task-space waypoints into joint trajectories using IK, verify poses via FK, and run repeatable... Read More
-
Application of Multimodal Large Language Model TOP NEW
In the ever-evolving field of artificial intelligence, the ability to interpret and analyze video content has opened new frontiers in understanding complex human activities. Gemini 1.5, a multimodal generative AI model developed by Google Cloud’s Vertex AI, is at the forefront of this revolution. In this blog post, we’ll explore how Gemini 1.5... Read More