No episode media available here
This is a representative still, not playable footage. Episode video for this dataset lives with its original source.
SACSoN Social Navigation
Human-aware indoor navigation
UC Berkeley RAIL
RobotData indexes this dataset's metadata. Attribution and licensing stay with the original publisher.
75 hours of autonomous navigation in busy university buildings with pedestrians in view, logging camera, LiDAR, odometry and actions plus human trajectories — collected to train socially compliant policies that minimise disruption to people.
Indexed episode structure
Per-episode numbers RobotData has indexed locally (camera count, DoF, control rate, success rate). "Not indexed yet" means we have not recorded that number — it does not mean the publisher's data lacks observations, state or actions. See the source-backed profile above for what the publisher documents.
2 cameras
2 DoF
5 Hz
Not indexed yet
Data modalities
Episode explorer
No episode media has been added for this dataset, so there is nothing to play. The explorer appears as soon as real clips exist — either uploaded here or extracted from the source.
Contribute episodesLinked models, robots & papers
Resolving related models, datasets and papers…
Related datasets
Real-world IndexedANYmal Perceptive Locomotion & Parkour
Source: ETH Robotic Systems Lab
- 21K
- 780
- 4
Real-world IndexedRT-1 Robot Action Dataset
Source: Google DeepMind Robotics
- 130K
- 17.4K
- 1
Real-world IndexedBC-Z Zero-Shot Task Generalization
Source: Google DeepMind Robotics
- 39K
- 218.6
- 1
Real-world IndexedDobb-E: Homes of New York
Source: NYU General-purpose Robotics & AI Lab
- 5.6K
- 13
- 1