UC Berkeley robot navigation could chart a new course for self

Using an image of a destination as reference, in this case, the house at the other side of the field, and "priors" about how to navigate overland on various kinds of terrain, gathered from hours of filmed video, an unmanned vehicle navigates nearly two miles on its own to reach its goal.

Shah et al. 2022

Robots and self-driving cars have one very large challenge in common, how to navigate the world. Typically, that task is approached by artificial intelligence as a problem of how to map the surroundings, to construct a precise overview of the geometry of a scene before a robot or a car moves across that terrain. 

There may be a simpler way. 

Electric Vehicles

• The 5 best electric cars: Plus, the cheapest EV available
• The top home EV chargers: Easily fuel up your car
• EV ownership is neither fairytale nor nightmare
• Our favorite electric lawn mowers: The best alternatives to gas-powered

In a paper posted on arXiv Wednesday by scholars at the University of California at Berkeley, a wheeled robot is able to travel kilometers over suburban terrain. 

The droid sticks to paths and dodges previously unseen obstacles. Essential is that it doesn't map its environment, as some other approaches have done, such as in autonomous driving AI programs. 

Instead, it relies on heuristics picked up from thirty hours of video of previous runs and some overhead maps of the terrain to create an improved schematic of the way stations along the way relate to one another, without a full map.

The research, titled "ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints," is authored by Ph.D. candidate Dhruv Shah and UC Berkeley assistant professor Sergey Levine. 

The ViKiNG program has increased its training data of camera observations from the random walk with an additional 12 hours of video that was from "teleoperated" trips, where a human guided the Jackal to pursue paths, such as sidewalks or hiking trails, to build up those prior examples. The neural network utilized to crunch all that training data is fairly humdrum, the familiar MobileNet convolutional neural network.

Artificial Intelligence

• AI in 2023: A year of breakthroughs that left no human thing unchanged
• These are the jobs most likely to be taken over by AI
• AI at the edge: 5G and the Internet of Things see fast times ahead
• Almost half of tech executives say their organizations aren't ready for AI or other advanced initiatives

This time, equipped with ViKiNG, Jackal goes well beyond the 80 meters of RECON, traveling from start to destination almost 3 kilometers away, or almost two miles.

In videos featured on a blog page for the project, Shah and Levine show how the Jackal with ViKiNG can figure out how to route around previously unknown obstacles, such as a parked vehicle blocking its path. A companion video explains the work, which you can view at the bottom of this post.

RECON explicitly employed elements of reinforcement learning. ViKiNG, likewise, borrows in some way. Asked about the connection to RL, Levine told ZDNetin an email, "I would characterize ViKiNG as a kind of reinforcement learning method with a higher level planner sitting on top of it."

This AI-powered prosthetic hand is bringing design and style to a life-changing product The best robot vacuums available now Why do college kids get all the cool robots? The 5 best robot mowers: Hands-free lawn care This AI-powered prosthetic hand is bringing design and style to a life-changing product

The best robot vacuums available now

Why do college kids get all the cool robots?

The 5 best robot mowers: Hands-free lawn care

Editorial standards Show Comments