Spatial Semantic Hierarchy (SSH)

Slides:



Advertisements
Similar presentations
Lecture 7: Potential Fields and Model Predictive Control
Advertisements

Lecture 8: Three-Level Architectures CS 344R: Robotics Benjamin Kuipers.
Motion Planning for Point Robots CS 659 Kris Hauser.
Graphs Chapter 12. Chapter Objectives  To become familiar with graph terminology and the different types of graphs  To study a Graph ADT and different.
University of Amsterdam Search, Navigate, and Actuate - Quantitative Navigation Arnoud Visser 1 Search, Navigate, and Actuate Quantative Navigation.
1 Enviromatics Spatial database systems Spatial database systems Вонр. проф. д-р Александар Маркоски Технички факултет – Битола 2008 год.
Computer Vision Laboratory 1 Unrestricted Recognition of 3-D Objects Using Multi-Level Triplet Invariants Gösta Granlund and Anders Moe Computer Vision.
Problem Solving and Search in AI Part I Search and Intelligence Search is one of the most powerful approaches to problem solving in AI Search is a universal.
Embedded System Lab Kim Jong Hwi Chonbuk National University Introduction to Intelligent Robots.
DESIGN OF A GENERIC PATH PATH PLANNING SYSTEM AILAB Path Planning Workgroup.
Introduction to Robotics In the name of Allah. Introduction to Robotics o Leila Sharif o o Lecture #2: The Big.
Paper Discussion: “Simultaneous Localization and Environmental Mapping with a Sensor Network”, Marinakis et. al. ICRA 2011.
A New Omnidirectional Vision Sensor for the Spatial Semantic Hierarchy E. Menegatti, M. Wright, E. Pagello Dep. of Electronics and Informatics University.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
ECE 4340/7340 Exam #2 Review Winter Sensing and Perception CMUcam and image representation (RGB, YUV) Percept; logical sensors Logical redundancy.
A Robot Exploration and Mapping Strategy Based on a Semantic Hierarchy of Spatial Representations Benjamine Kuipers and Yung-Tai Byun Tai S. Jang MAE University.
Graphs Chapter 12. Chapter 12: Graphs2 Chapter Objectives To become familiar with graph terminology and the different types of graphs To study a Graph.
Behavior Coordination Mechanisms – State-of-the- Art Paper by: Paolo Pirjanian (USC) Presented by: Chris Martin.
Geometric Conceptual Spaces Ben Adams GEOG 288MR Spring 2008.
오 세 영, 이 진 수 전자전기공학과, 뇌연구센터 포항공과대학교
DARPA Mobile Autonomous Robot SoftwareLeslie Pack Kaelbling; March Adaptive Intelligent Mobile Robotics Leslie Pack Kaelbling Artificial Intelligence.
© Manfred Huber Autonomous Robots Robot Path Planning.
CS654: Digital Image Analysis Lecture 3: Data Structure for Image Analysis.
1 CO Games Development 1 Week 6 Introduction To Pathfinding + Crash and Turn + Breadth-first Search Gareth Bellaby.
9 Introduction to AI Robotics (MIT Press), copyright Robin Murphy 2000 Chapter 9: Topological Path Planning1 Part II Chapter 9: Topological Path Planning.
Edge Linking & Boundary Detection
Simultaneous Localization and Mapping Presented by Lihan He Apr. 21, 2006.
Intelligent Vision Systems ENT 496 Object Shape Identification and Representation Hema C.R. Lecture 7.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
110/19/2015CS360 AI & Robotics AI Application Areas  Neural Networks and Genetic Algorithms  These model the structure of neurons in the brain  Humans.
University of Amsterdam Search, Navigate, and Actuate - Qualitative Navigation Arnoud Visser 1 Search, Navigate, and Actuate Qualitative Navigation.
Mobile Robot Navigation Using Fuzzy logic Controller
Ground Truth Free Evaluation of Segment Based Maps Rolf Lakaemper Temple University, Philadelphia,PA,USA.
1 Spatial Data Models and Structure. 2 Part 1: Basic Geographic Concepts Real world -> Digital Environment –GIS data represent a simplified view of physical.
9 Introduction to AI Robotics (MIT Press), copyright Robin Murphy 2000 Chapter 9: Topological Path Planning1 Part II Chapter 9: Topological Path Planning.
Using RouteGraphs as an Appropriate Data Structure for Navigational Tasks SFB/IQN-Kolloquium Christian Mandel, A1-[RoboMap] Overview Goal scenario.
Non-Manifold Multi-Tesselations From Meshes to Iconic Representations of Objects L. De Floriani, P. Magillo, E. Puppo, F. Morando DISI - University of.
1 Solving problems by searching 171, Class 2 Chapter 3.
Topological Path Planning JBNU, Division of Computer Science and Engineering Parallel Computing Lab Jonghwi Kim Introduction to AI Robots Chapter 9.
UNC Chapel Hill M. C. Lin Introduction to Motion Planning Applications Overview of the Problem Basics – Planning for Point Robot –Visibility Graphs –Roadmap.
Chapter 10. The Explorer System in Cognitive Systems, Christensen et al. Course: Robots Learning from Humans On, Kyoung-Woon Biointelligence Laboratory.
9 Introduction to AI Robotics (MIT Press), copyright Robin Murphy 2000 Chapter 9: Topological Path Planning1 Part II Chapter 9: Topological Path Planning.
Graphs Chapter 12. Chapter 12: Graphs2 Chapter Objectives To become familiar with graph terminology and the different types of graphs To study a Graph.
Fast SLAM Simultaneous Localization And Mapping using Particle Filter A geometric approach (as opposed to discretization approach)‏ Subhrajit Bhattacharya.
Preparing for Algebra Chapter Plan for Problem Solving Pg. P5-P6 Obj: Learn how to use the four-step problem- solving plan.
Ghislain Fouodji Tasse Supervisor: Dr. Karen Bradshaw Computer Science Department Rhodes University 04 August 2009.
Chapter 21 Robotic Perception and action Chapter 21 Robotic Perception and action Artificial Intelligence ดร. วิภาดา เวทย์ประสิทธิ์ ภาควิชาวิทยาการคอมพิวเตอร์
May 2003 SUT Color image segmentation – an innovative approach Amin Fazel May 2003 Sharif University of Technology Course Presentation base on a paper.
Autonomous Robots Robot Path Planning (2) © Manfred Huber 2008.
Vision-Guided Humanoid Footstep Planning for Dynamic Environments
COGNITIVE APPROACH TO ROBOT SPATIAL MAPPING
Software Engineering (CSI 321)
Instance Based Learning
CS b659: Intelligent Robotics
State Machines Chapter 5.
Part II Chapter 9: Topological Path Planning
Artificial Intelligence
CSCTR – Session 6 Dana Retová
Logical architecture refinement
CSc4730/6730 Scientific Visualization
CIS 488/588 Bruce R. Maxim UM-Dearborn
Artificial Intelligence Chapter 2 Stimulus-Response Agents
Robot Intelligence Kevin Warwick.
Discrete Controller Synthesis
Market-based Dynamic Task Allocation in Mobile Surveillance Systems
CO Games Development 1 Week 8 Depth-first search, Combinatorial Explosion, Heuristics, Hill-Climbing Gareth Bellaby.
Functions and Graphing
Representation of Color Stimuli in Awake Macaque Primary Visual Cortex
Planning.
Presentation transcript:

Spatial Semantic Hierarchy (SSH) What is it? How is it related to robot localization and mapping? 9/17/2018 CMSC828F-Perceptual Robotics

Presentation Structure Overview of SSH Applications of SSH to robot localization and navigation Discussion 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics References [1] “The Spatial Semantic Hierarchy”, B. Kuipers, AI 119 (2000) pg 191-233 [2] “An intellectual History of the Spatial Semantic Hierarchy”, B. Kuipers, in M. Jefferies and A. Yeap (Eds.), “Robot and Cognitive Approaches to Spatial Mapping”, Springer Verlag, 2006 [3] “Local metrical and global topological maps in the Hybrid Spatial Semantic Hierarchy”, B. Kuipers, J. Modayil, P. Beeson, M. MacMahon, and F. Savell, ICRA 2004. [4] “Towards Autonomous Topological Place Detection Using the Extended Voronoi Graph”, P. Beeson, N. K. Jong and B. Kuipers, ICRA 2005 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Types of spaces Visual Space Surrounding environment Large-scale Space Scale larger than the sensory horizon of the agent Graphical (Diagrammatic) Space Spatial layout and relations among symbols on paper 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Overview of SSH A hierarchical description of a cognitive map, consisting of four different levels Each level defines its own ontology (i.e. types of objects+relations among them) Each level is grounded in the ones below Low to high level knowledge organization Combines qualitative and quantitative information 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics SSH Structure (copied from “The Spatial Semantic Hierarchy” paper [1]) 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Vertical Axis Sensory Level Control Level Causal Level Topological Level Metrical Level 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Horizontal Axis Qualitative Quantitative Continuous valued variables Analog models of space 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Control Level Provides an abstraction from the continuous sensory input and motor output to discrete states Agent representation includes a set of control laws, a selection method and termination conditions for each control law Agent, environment and control law form a continuous dynamical system 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics States Locally distinctive state is a local maximum state with respect to a distinctiveness measure Possible distinctiveness measures equidistance from nearby obstacles (hill-climbing control law case) sudden change in trajectory (trajectory-following control law case) 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Control Laws Hill-climbing control laws : bring the agent to a locally-distinctive state from any state within the local neighborhood Trajectory-following control laws : bring the agent from one distinctive state to the neighborhood of the next 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Control law selection Many different strategies Rule-based system Decision-tree, based on sensory input Combination of multiple laws using fuzzy control, potential field methods etc. Smooth transitions between control laws can be implemented with weighted average of appropriateness measures. 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Local 2-D geometry (1) Different methods for map-building and localization Occupancy grids Split space into cells Each cell holds a number containing the probability of being occupied Sensory target map Identify and localize objects Size of the maps depends on the number of objects 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Local 2-D geometry (2) Model the path as a “generalized cylinder” Different characteristics of the cylinder might be known with different accuracy/confidence Good to incorporate weak metrical information with strong one 9/17/2018 CMSC828F-Perceptual Robotics

Guarantees at the control level Alternating trajectory-following and hill-climbing control laws using the following closure criteria For all states, there exist a trajectory-following control law (no dead ends) For all trajectory-following control laws executed at an appropriate state, there exist at least one hill-climbing control law available 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Causal Level Action A: Sequence of control laws taking the agent from a distinctive state to another View V: Description of the sensory input vector s(t) Schema: A tuple (V,A,V’) Declarative meaning/ Situation calculus Procedural meaning/ Stimulus-response pair Routine: Set of schemas 9/17/2018 CMSC828F-Perceptual Robotics

Situation Calculus (1): Overview First-order language extended with an extra situation argument Holds(V,s0) = view V is observed in situation s0 “do” function applies an action to a situation to yield a new situation “result(A, s0)” denotes the new situation after applying action A to situation s0 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Situation Calculus (2) Action representation Used in AI Planning Resulting planners are efficient if domain specific search control knowledge is used 9/17/2018 CMSC828F-Perceptual Robotics

Action categorization Two (rough) categories: turns and travels Turn: Leaves the agent at the same place Travel: Takes the agent from one place to another Also depends on the motor and sensor capabilities of the agent 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Topological Level Describes the environment as a collection of Places eq. to zero-dimensional points Paths eq. To one-dimensional subspaces (lines) Regions eq. two-dimensional subset of space, i.e. sets of places binded together Also exist topological relations and axioms Abduction is used to find places and paths from views and actions 9/17/2018 CMSC828F-Perceptual Robotics

Hierarchy in Topological Level There are multiple topological maps with different granularity. Abstraction region represents the set of places that is abstracted to a single node in a higher level map Upward mapping: Each node of the lower lvl corresponds to its abstraction region Downward mapping: Inverse procedure 9/17/2018 CMSC828F-Perceptual Robotics

Topological relations At(view, place) : view seen at place Along(view, path, dir) : view seen along path in direction dir On(place,path) : place on path Order(path,place1, place2, dir) : order on path from place1 to place2 is dir Right_of(path,dir, region)/left_of : path facing direction dir has region on its right/left In(place, region) : place is in region 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Metrical Level A global 2-D analog representation of the world Not necessary for the SSH to work Can lead to more accurate global localization, when perceptual aliasing (i.e. distinct places appear similar) is present 9/17/2018 CMSC828F-Perceptual Robotics

Metrical Level Creation Problems Useful states of knowledge might not be expressible as global coordinates “around the block” and “walking in circles” problem High requirements in space and time Possible solution is to use a loosely-coupled collection of local “patch” maps 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Extensions of SSH Combine large and small-scale perceptual space SSH treats perception as a black-box Better definition of distinctive states Hill-climbing is unnecessary in some cases Connect SSH with SLAM 9/17/2018 CMSC828F-Perceptual Robotics

Hybrid Spatial Semantic Hierarchy Create a local perceptual map based on SLAM methods Use the local map for localization Identify gateways, i.e. places where control shifts from motion between places to localization within a neighborhood Identify path fragments connecting distinct places Create a local topology that describes how directed path segments join at a place 9/17/2018 CMSC828F-Perceptual Robotics

Advantages of Hybrid SSH Hill-climbing not required More accurate identification of places using local topological and perceptual map 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Questions? 9/17/2018 CMSC828F-Perceptual Robotics

CMSC828F-Perceptual Robotics Thank you 9/17/2018 CMSC828F-Perceptual Robotics