Robots’ maps of their environments can make existing object-recognition algorithms more accurate.
John Leonard’s group in the MIT Department of Mechanical Engineering specializes in SLAM, or simultaneous localization and mapping, the technique whereby mobile autonomous robots map their environments and determine their locations.
Last week, at the Robotics Science and Systems conference, members of Leonard’s group presented a new paper demonstrating how SLAM can be used to improve object-recognition systems, which will be a vital component of future robots that have to manipulate the objects around them in arbitrary ways.
The system uses SLAM information to augment existing object-recognition algorithms. Its performance should thus continue to improve as computer-vision researchers develop better recognition software, and roboticists develop better SLAM software.
“Considering object recognition as a black box, and considering SLAM as a black box, how do you integrate them in a nice manner?” asks Sudeep Pillai, a graduate student in computer science and engineering and first author on the new paper. “How do you incorporate probabilities from each viewpoint over time? That’s really what we wanted to achieve.”
Despite working with existing SLAM and object-recognition algorithms, however, and despite using only the output of an ordinary video camera, the system’s performance is already comparable to that of special-purpose robotic object-recognition systems that factor in depth measurements as well as visual information.
And of course, because the system can fuse information captured from different camera angles, it fares much better than object-recognition systems trying to identify objects in still images.
Read more: Object recognition for robots
The Latest on: Robotic object-recognition systems
[google_news title=”” keyword=”robotic object-recognition systems” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robotic object-recognition systems
- Indoor Service Robot Design with ROS and Deep Learningon April 23, 2024 at 4:32 pm
In a recent paper published in the journal Machines , researchers from China presented the design of an intelligent indoor service robot capable of performing tasks like precise object recognition, ...
- Air Force selects Stratom to develop machine learning-driven system for asset trackingon April 23, 2024 at 10:16 am
The first-of-its-kind system offers a leap in asset tracking efficiency, enhancing global logistics operationsLOUISVILLE, CO, April 23, 2024 (GLOBE NEWSWIRE) -- Stratom today announced its selection ...
- Video: Bio-inspired aquatic robot shoots through the water like a penguinon April 18, 2024 at 11:21 am
Penguins are fast, fantastic swimmers, so why not make an underwater robot inspired by them? That's just what German underwater tech company EvoLogics has done, with its new-and-improved Quadroin AUV ...
- New home monitoring system promises to launch paintballs at intruderson April 16, 2024 at 5:02 am
OZ-IT’s artificial intelligence (AI) surveillance system, dubbed PaintCam Eve, is an autonomous property monitoring device designed to protect homeowners from burglars, intruders and even unwanted ...
- The Smarter Future Of Data Capture: Uncovering New Layers Of Intelligenceon April 16, 2024 at 3:00 am
In terms of current innovations, the new Apple Vision Pro is a great example of augmented reality’s significant and growing applications for the enterprise as well as for consumers. But there’s little ...
- Startup pitches a paintball-armed, AI-powered home security cameraon April 15, 2024 at 7:51 am
Experience ultimate peace of mind,” PaintCam’s website declares, as Eve will offer owners a “perfect fusion of video security and physical presence” thanks to its “unintrusive [sic] design that stands ...
- Meta AI releases OpenEQA to spur ’embodied intelligence’ in artificial agentson April 11, 2024 at 5:18 pm
Meta AI releases OpenEQA, a new open-source benchmark dataset to measure AI's ability to understand and answer questions about real-world environments, advancing embodied AI research.
- Generation of machines: How robots help Moscowon April 8, 2024 at 2:00 pm
Robots are becoming part of everyday life in Moscow. Smart machines clean spaces, deliver medicines, check health and improve operational quality and efficiency.
- The best robot vacuum cleaners, tried and tested at homeon March 27, 2024 at 4:21 am
Should I get a robot vacuum cleaner ... It also has excellent object recognition, navigating around socks and even tiny toys rather than trying to suck them up. One clever feature is its Dirt ...
- Robots learn to feel betteron March 4, 2024 at 2:42 pm
This can allow robotic systems to analyse an object’s shape ... such as gesture recognition. The performance of the sensors in the contact and non-contact system also reflects its potential ...
via Bing News