COMP 50: Autonomous Class tomorrow and 2/26 Intelligent Robotics ● Research Lecture homework: by the end of the semester, attend and write a response to one of the following talks Instructor: Jivko Sinapov http://www.cs.tufts.edu/comp/50AIR/ Derry Wijaya Today: Planning Aylin Caliskan Thursday 2/22 Monday 2/26 3:00 pm 3:00 pm TOPIC: TOPIC: Natural Language Processing Bias in AI and ML Allison Chaney Naomi Fitter Tuesday 3/13 Monday 3/12 3:00 pm 9:30 am TOPIC: TOPIC: Human-Centered ML Human-Robot Cooperation Announcements Class Projects ● Design Projects ● Infrastructure Projects ● Demo and Application Projects ● Combination of the above
Design Projects Demo Projects ● Message and object delivery ● “cocktail” robot (e.g., for a conference setting) ● Robot that looks for trash on the floor ● Robot that plays a game... ● …. Design Projects (2) Infrastructure Projects ● Design a mobile manipulator using mobile ● Semantic mapping – add a layer of semantics to the metric map that the robot currently has bases, robot arms, and sensors that are currently on the market ● Symbolic planning – add symbolic actions and STRIPS-like planning ● Enable 3D mapping – there are many packages and libraries that exist but are largely experimental ● Enhance visual perception – train classifiers to recognize specific objects of interest Design in Simulation “What can the robot do?”
Teleoperation Next Steps ● Team formation: By Friday, Feb. 22 – Look for a link to shared doc on Trunk ● Preliminary “Presentations” – Wed. Feb 28 – Lightning talks: < 5 min – 2-3 slides (enter link in shared doc) – Pitch 2-3 ideas for a class project to get feedback from me and the rest of the class Teleoperation Planning [http://www.cs.colostate.edu/~cs540/spr2018/res_images/cs540logo.gif] Teleoperation Teleoperation
Teleoperation Teleoperation vs Telepresence ● An early attempt to improve teleoperation was to add more cameras / displays ● Telepresence aims for placing the operator in a virtual reality that mimics the robot's surroundings Teleoperation Telepresence Robots http://www.pilotpresence.com/wp-content/uploads/2011/01/remote-presence-systemsv2.jpg Robotics Timeline The need for (semi-) autonomy
The Early Answer (1967): Sense-Plan-Act How should autonomy be achieved and organized? Early Example of S-P-A Robot Primitives Early Work on Planning The Early Answer (1967): Sense-Plan-Act
Early Work on Planning A More Realistic Example A More Realistic Example Early Work on Planning A More Realistic Example IT Is INROOM(IT,R1) true or false? CONNECTS(D1,R1,R2)? INROOM(IT,R2)? A More Realistic Example Representing Initial State IT
Representing Goal State Finding the Plan IT The “difference” table Discussion ● How did you solve the problem? ● What are some limitations of planning with STRIPS? ● Where do the predicates, operators, etc. come from? Logical Difference Towers of Hanoi with PDDL or [ https://s3.amazonaws.com/ka-cs-algorithms/hanoi-5-init.png ]
PDDL Predicates ● Editor: http://editor.planning.domains/ ● clear(x): true if x is clear, smaller(x1,x2): true if x1 is smaller than x2, ontop(x1,x2), disk(x1), peg(x1) ● Tutorial: https://www.cs.toronto.edu/~sheila/2542/s14/A1/ ● Move Action variables: dx – the disk we are moving introtopddl2.pdf – dy: destination disk/peg – du: the disk/peg under dx ● Example PDDL files: – Preconditions: smaller(dx, dy), clear(dy), clear(dx), http://www.ida.liu.se/%7ETDDC17/info/labs/plann ontop(dx,du) ing/strips/ – Effects: not clear(dy), not ontop(dx,du), clear(du), ontop(dx,dy), Formulating the problem Actions ● Step 1: specify predicates ● Action name and parameters: ● Step 2: specify actions with preconditions and ● Preconditions: effects ● Effects: 3-Disk Hanoi Final Plam
PDDL Excercise ● Formulate the domain and problem for the robot navigation example Project Team-up Activity THE END
Recommend
More recommend
