Social navigation is an AI technology that enables robots to move through human spaces smoothly and predictably by understanding human intentions and communicating its own plans, solving the 'phrasing problem' where traditional robots stop and hesitate when encountering people. This technology relies on two key features: anticipation (predicting human movements) and communication (explaining robot intentions), making it an intelligence problem rather than a hardware challenge.
Deep Dive
Prerequisite Knowledge
- No data available.
Where to go next
- No data available.
Deep Dive
What is social navigation? CTO of the leading physical AI company in Japan
Added:Hi there, I'm Sattorra from Canary Tech and it's our first YouTube vlog and let's ask our CTO Alishar to tell us about Canary Tech. Hi Alishair.
>> Hi.
>> Can I have 5 minutes of your time?
>> Sure.
>> Can you explain what Canary Tech builds?
>> Yeah, building social brain for robot navigation.
>> What is social navigation and how is it different from existing robot navigations? Well, before explaining what social navigation is, let me explain you the the current challenges with the current robot navigation. Um, the biggest problem is phrasing problem which means when robots are moving in the static environment and they first of all they do the mapping of this space and then while they are navigating they are moving according to this map.
However, when there are people around uh these robots usually stops quite a lot because um when humans are around, robots don't know what to do and they are very hesitant to what action to take next and sometimes they are blocking the aisles, blocking the roads and also um um and they are waiting for people to open up space for them. So this is called phrasing problem with the current robot navigation.
>> I see. Uh why this happens with current navigation solutions. This phrasing problem is happening because in static environment there are no moving objects but humans are always moving and they especially moving with the intent with the intention and that means if robot cannot understand human intentions uh which means predicting the future movements of people then robots are um cannot come up with what to do at that given time. So that's why they usually stop and then try to rethink what to do next. And imagine if the space is very much crowded then this um stopping and rethinking happen happens one after another which is end up with phrasing problem.
>> Thank you. Back to my previous question.
So what is the social navigation? Social navigation is um moving the robots in the human spaces the way we naturally would do which means like smoother navigation and predictable and also socially aware.
>> I see this is very much required technology to make robots a commodity and um what makes this technology possible?
>> We think there's two main features which makes this technology possible. One is anticipation and the second one is communication. Antich anticipation is about predicting the next movement of people around so that can understand the intentions and then they can do the planning ahead. So this is one um very important feature which makes the social navigation possible. The second one is a communication and by communication what we mean is robot has to uh explain itself explain its own intentions so that and people can also understand what robot is thinking and what robot is planning to do next and so you can think this as a two ways. So on one side robot understanding human intentions to make um the navigation and on the other side people would understand robot intention so that they can communicate with the robot and they can understand robot intention and and plans for next movements. So these two things makes the social navigation possible.
>> Thank you so much. Uh is there any last comments you would like to add? Yeah, in Canary Tech we think this social robot navigation is not a hardware problem.
This is an intelligence problem. So this is what we are building. We are building the intelligence layer, the brain for robots so that they will be socially aware so that they can share spaces with us and then uh working with the human in a harmony. Thank you.
Related Videos

Setting up a curved screen with Immersive Calibration Pro 4 and multiple cameras (P3D v4)
FlyerOneZero
23K views•2019-07-21

Robot Learning with Sparsity and Scarcity
allenai
379 views•2025-10-14

Jorge Mendez-Mendez: Unlocking Lifelong Robot Learning With Modularity (2023-10-05)
umassmlfl
237 views•2024-01-06

Northwestern’s MS in Robotics: Student Robotics Projects, 2023
NorthwesternEngineering
1K views•2024-05-31

"Perfect" Turns: Turning by the Gyro - FIRST LEGO League (FLL) SPIKE Prime + EV3 RePlay Programming
ZacharyTrautwein
94K views•2020-10-02

Gorkem Secer: TSLIP-based Deadbeat Running Control of Bipedal Robot ATRIAS
DynamicWalking-wv6qm
298 views•2018-06-22

Self-Driving Cars Need Lessons On Human Drivers | Maddie About Science
skunkbear
26K views•2018-08-21

Milrem Robotics’ THeMIS UGVs used in a live-fire manned-unmanned teaming exercise
MilremRobotics
99K views•2021-05-20
Trending

WOW! Judge TURNS THE TABLES on Trump in His OWN $10B LAWSUIT!!!
MeidasTouch
197K views•2026-07-23

Playstation NO DISC/NO BUY Fight Is Over...
DavidJaffeGames
4K views•2026-07-23

Steam and Xbox Just Dropped The Hammer On PlayStation
OhNoItsAlexx
9K views•2026-07-23

Americans Confused in Australia for 17 Minutes Straight
IWrocker
17K views•2026-07-23