# Bharath Sankaran

- **Website:** <https://bharathsankaran.com>
- **Primary alias:** `bharathsankaran.com`

## Description

Bharath Sankaran is a roboticist, computer scientist, and entrepreneur whose work focuses on using movement and interaction to help intelligent systems understand complex real-world environments. Based in Zürich, he is with Reality Labs at Meta, where he works on deep-tech augmented and virtual reality products drawing on artificial intelligence, computer vision, graphics, machine learning, sensor fusion, and hardware. His career includes serving as vice president of product and leading manipulation efforts at ANYbotics, as well as co-founding Naska.AI, formerly Scaled Robotics, where he was chief technology officer for seven years.

Sankaran’s research spans autonomy for ground, aerial, and humanoid robots. Key areas include vision-based navigation in unfamiliar and changing environments, robust 3D recognition, active and interactive perception, and shared autonomy that combines robotic capabilities with human supervision. His work aims to help autonomous systems build useful representations and operate reliably in unstructured settings. He invites inquiries about research collaborations and proposals, and provides information for prospective internship and thesis students through his research projects.

## Industries

- 🖥 Computers Electronics and Technology
- 🖥 Augmented Reality and Virtual Reality _(under Computers Electronics and Technology)_

## Links

- [twitter](https://twitter.com/BharathSankara1)

## Logos & icons

- logo _(primary)_ — PNG — [download](https://cdn.brandfetch.io/id6_BMd0IO/w/180/h/180/theme/dark/logo.png?c=1bxid64Mup7aczewSAYMX&t=1791528389913)

## Colors

| Name | Hex | Theme |
| --- | --- | --- |
| Trout | #474753 | accent |
| Bunker | #030406 | dark |
| Tussock | #cc8b57 | light |

## Fonts

- Arial — asset _(custom)_

---

_Source: <https://brandfetch.com/bharathsankaran.com>_
_See [/llms.txt](/llms.txt) for a full list of agent-readable pages, and [/auth.md](/auth.md) for how agents authenticate._