DOC PREVIEW
USC CSCI 561 - session26-27

This preview shows page 1-2-22-23 out of 23 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 23 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 23 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 23 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 23 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 23 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

CS 561, Sessions 26-271Towards intelligent machinesThanks to CSCI561, we now know how to…- Search (and play games)- Build a knowledge base using FOL- Use FOL inference to ask questions to the KB-PlanAre we ready to build the next generation of super-intelligent robots?CS 561, Sessions 26-272Some problems remain…•Vision• Audition / speech processing• Natural language processing• Touch, smell, balance and other senses• Motor controlCS 561, Sessions 26-273Computer Perception• Perception: provides an agent information about its environment. Generates feedback. Usually proceeds in the following steps.1. Sensors: hardware that provides raw measurements of properties of the environment1. Ultrasonic Sensor/Sonar: provides distance data2. Light detectors: provide data about intensity of light3. Camera: generates a picture of the environment2. Signal processing: to process the raw sensor data in order to extract certain features, e.g., color, shape, distance, velocity, etc.3. Object recognition: Combines features to form a model of an object4. And so on to higher abstraction levelsCS 561, Sessions 26-274Perception for what?• Interaction with the environment, e.g., manipulation, navigation• Process control, e.g., temperature control• Quality control, e.g., electronics inspection, mechanical parts• Diagnosis, e.g., diabetes • Restoration, of e.g., buildings • Modeling, of e.g., parts, buildings, etc.• Surveillance, banks, parking lots, etc.•… • And much, much moreCS 561, Sessions 26-275Image analysis/Computer vision1. Grab an image of the object (digitize analog signal)2. Process the image (looking for certain features)1. Edge detection2. Region segmentation3. Color analysis4. Etc.3. Measure properties of features or collection of features (e.g., length, angle, area, etc.)4. Use some model for detection, classification etc.CS 561, Sessions 26-276Image Formation and Vision Problem• Image: is a 2D projection of a 3D scene. Mapping from 3D to 2D, i.e., some information is getting lost.• Computer vision problem: recover (some or all of) that information. The lost dimension 2D à 3D(Inverse problem of VR or Graphics)Challenges: noise, quantization, ambiguities, illumination, etc.• Paradigms:• Reconstructive vision: recover a model of the 3D scene from 2D image(s) (e.g., shape from shading, structure from motion)More general• Purposive vision: recover only information necessary to accomplish task (e.g., detect obstacle, find doorway, find wall).More efficientCS 561, Sessions 26-277How can we see?• Marr (1982): 2.5D primal sketch1) pixel-based (light intensity)2) primal sketch (discontinuities in intensity)3) 2 ½ D sketch (oriented surfaces, relative depth between surfaces)4) 3D model (shapes, spatial relationships, volumes)CS 561, Sessions 26-278State of the art• Can recognize faces?• Can find salient targets?• Can recognize people?• Can track people and analyze their activity?• Can understand complex scenes?CS 561, Sessions 26-279State of the art• Can recognize faces? – yes, e.g., von der Malsburg (USC)• Can find salient targets? – sure, e.g., Itti (USC) or Tsotsos (York U)• Can recognize people? – no problem, e.g., Poggio (MIT)• Can track people and analyze their activity? – yep, we saw that (Nevatia, USC)• Can understand complex scenes? – not quite but in progressCS 561, Sessions 26-2710Face recognition case study• C. von der Malsburg’s lab at USCCS 561, Sessions 26-2711Finding “interesting” regions in a sceneCS 561, Sessions 26-2712Visual attentionCS 561, Sessions 26-2713Visual AttentionCS 561, Sessions 26-2714Pedestrian recognition• C. Papageorgiou & T. Poggio, MITCS 561, Sessions 26-2715CS 561, Sessions 26-2716How about other senses?• Speech recognition -- can achieve user-undependent recognition for small vocabularies and isolated words• Other senses -- overall excellent performance (e.g., using gyroscopes for sense of balance, or MEMS sensors for touch) except for olfaction and taste, which are very poorly understood in biological systems also.CS 561, Sessions 26-2717How about actuation• Robots have been used for a long time in restricted settings (e.g., factories) and, mechanically speaking, work very well.• For operation in unconstrained environments, Biorobotics has proven a particularly fruitful line of research:Motivation: since animals are so good at navigating through their natural environment, let’s try to build robots that share some structural similarity with biological systems.CS 561, Sessions 26-2718Robot examples: constrained environmentsCS 561, Sessions 26-2719Robot examples: towards unconstrained environmentsSee Dr. Schaal’s lab at http://www-clmc.usc.eduCS 561, Sessions 26-2720More robot examplesRhex, U. MichiganCS 561, Sessions 26-2721More robotsUrbie @ JPL and robots from iRobots, Inc.CS 561, Sessions 26-2722Outlook• It is a particularly exciting time for AI because…- CPU power is not a problem anymore- Many physically-capable robots are available- Some vision and other senses are partially available- Many AI algorithms for constrained environment are availableSo for the first time YOU have all the components required to build smart robots that interact with the real world.CS 561, Sessions 26-2723Hurry, you are not alone…Robot mowers and vacuum-cleaners are here


View Full Document

USC CSCI 561 - session26-27

Download session26-27
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view session26-27 and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view session26-27 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?