appld adaptive planner parameter learning from
play

APPLD: Adaptive Planner Parameter Learning From Demonstration Xuesu - PowerPoint PPT Presentation

Jul 27, 2023 •411 likes •530 views

APPLD: Adaptive Planner Parameter Learning From Demonstration Xuesu Xiao 1* , Bo Liu 1* , Garrett Warnell 2 , Jonathan Fink 2 , and Peter Stone 1 1 The University of Texas at Austin 2 Army Research Laboratory * Equally Contributing Authors 1 LfD

  1. APPLD: Adaptive Planner Parameter Learning From Demonstration Xuesu Xiao 1* , Bo Liu 1* , Garrett Warnell 2 , Jonathan Fink 2 , and Peter Stone 1 1 The University of Texas at Austin 2 Army Research Laboratory * Equally Contributing Authors 1

  2. LfD for Improved Robot Navigation Motivation: Deploying an autonomous navigation system in a new environment is not as straightforward as it may seem. 2

  3. LfD for Improved Robot Navigation Inspiration: Humans do this effortlessly. 3

  4. LfD for Improved Robot Navigation Central Question: Can we squeeze more robust performance out of our existing navigation systems using LfD and limited human interaction? LfD? ROS move_base navigation stack 4

  5. LfD for Improved Robot Navigation Proposed : Use behavioral cloning to “tune” any navigation stack. tuning parameters sensor data motor commands Behavioral Cloning : Learn parameters from a demonstration using supervised learning. 5

  6. LfD for Improved Robot Navigation Context Problem: Humans exhibit qualitatively different navigation behaviors in qualitatively different environments. 6

  7. LfD for Improved Robot Navigation APPLD: Adaptive planner parameter learning from demonstration 1. Collect demonstration. 2. Perform automatic demonstration segmentation. 3. Use black-box optimization to find set of optimal parameters. 4. Use supervised learning to train a context predictor. 7

  8. LfD for Improved Robot Navigation APPLD Deployment 8

  9. LfD for Improved Robot Navigation Experiments Robot : Clearpath Jackal (Velodyne Puck lidar) Human : An author (Xbox wireless controller) Environment : Challenging obstacle course 9

  10. Results APPLD: Deployment in demonstration environment 10

  11. Results Xuesu Xiao xiao@cs.utexas.edu Different robot, navigation stack, and environment 11

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

The Use of EduPRO System for Adaptive Learning Process Organizing Benefits of adaptive e

The Use of EduPRO System for Adaptive Learning Process Organizing Benefits of adaptive e

Vasyl Stefanyk Precarpathian National University Centre of Distance Learning The Use of EduPRO System for Adaptive Learning Process Organizing Benefits of adaptive e learning system Formation of the individual structure of the material;

396 views • 10 slides
with Adaptive Learning LEARN MORE THAN YOU EVER IMAGINED - AT A PACE YOU DIDN'T THINK POSSIBLE

with Adaptive Learning LEARN MORE THAN YOU EVER IMAGINED - AT A PACE YOU DIDN'T THINK POSSIBLE

Creating Impact at Scale with Adaptive Learning LEARN MORE THAN YOU EVER IMAGINED - AT A PACE YOU DIDN'T THINK POSSIBLE WHAT IS ADAPTIVE LEARNING? An online delivery method that automatically adjusts to the needs of each learner.

85 views • 6 slides
What is your primary job function? A. Association Meeting Planner B. Third-party Meeting Planner

What is your primary job function? A. Association Meeting Planner B. Third-party Meeting Planner

Young Professional Lunchtime Learning: Best Practices for the New & Mid-level Meeting Planner Aaron D. Wolowiec, MSA, CAE, CMP Lloyd Doubleday III, CMP Director, Education & Associate Partnerships Director of Event Planning Health

424 views • 5 slides
Adaptive Learning Meets Crowdsourcing Towards Development of Cost-Effective Adaptive Educational

Adaptive Learning Meets Crowdsourcing Towards Development of Cost-Effective Adaptive Educational

Adaptive Learning Meets Crowdsourcing Towards Development of Cost-Effective Adaptive Educational Systems Dr Hassan Khosravi The University of Queensland Brisbane, QLD, Australia h.khosravi@uq.edu.au Adaptive Learning Meets Crowdsourcing

580 views • 32 slides
CS 6453: Parameter Server Soumya Basu March 7, 2017 What is a Parameter Server? Server for

CS 6453: Parameter Server Soumya Basu March 7, 2017 What is a Parameter Server? Server for

CS 6453: Parameter Server Soumya Basu March 7, 2017 What is a Parameter Server? Server for large scale machine learning problems Machine learning tasks in a nutshell: Feature (1, 1, 1) Training Extraction (2, -1, 3) (5, 6, 7)

520 views • 21 slides
Augmenting the Planner with Machine Learning Manchester PostgreSQL Meetup Anthony Kleerekoper

Augmenting the Planner with Machine Learning Manchester PostgreSQL Meetup Anthony Kleerekoper

Augmenting the Planner with Machine Learning Manchester PostgreSQL Meetup Anthony Kleerekoper Augmenting the Planner 27 May 2015 1 Example Query SELECT sum(l_extendedprice * l_discount) as revenue FROM lineitem WHERE l_shipdate >=

771 views • 64 slides
An Adaptive Tutor to Promote Learners Skills Acquisition during Procedural Learning Joanna

An Adaptive Tutor to Promote Learners Skills Acquisition during Procedural Learning Joanna

An Adaptive Tutor to Promote Learners Skills Acquisition during Procedural Learning Joanna TAOUM Workshop eliciting Adaptive Sequences for Learning ITS, Montral ( Canada ) , June 2018 CONTEXT Actions and Procedures on ECA Positive

401 views • 28 slides
Context-specific independence Parameter learning: MLE Graphical Models 10708 Carlos Guestrin

Context-specific independence Parameter learning: MLE Graphical Models 10708 Carlos Guestrin

Use Chapter 3 of K&F as a reference for CSI Reading for parameter learning: Chapter 12 of K&F Context-specific independence Parameter learning: MLE Graphical Models 10708 Carlos Guestrin Carnegie Mellon University October 5 th ,

613 views • 45 slides
Bayesian networks: basic parameter learning Machine Intelligence Thomas D. Nielsen September

Bayesian networks: basic parameter learning Machine Intelligence Thomas D. Nielsen September

Bayesian networks: basic parameter learning Machine Intelligence Thomas D. Nielsen September 2008 Basic parameter learning September 2008 1 / 24 Estimation Example: Physical Measurements Mass of an atomic particle is measured in repeated

798 views • 46 slides
Introduction to Machine Learning Linear Regression Prof. Andreas Krause Learning and Adaptive

Introduction to Machine Learning Linear Regression Prof. Andreas Krause Learning and Adaptive

Introduction to Machine Learning Linear Regression Prof. Andreas Krause Learning and Adaptive Systems (las.ethz.ch) Basic Supervised Learning Pipeline Training Data Test Data spam ? Learning Predic- ham Model method ?

566 views • 23 slides
Parameter-Efficient Transfer Learning for NLP N. Houlsby, A. Giurgiu*, S. Jastrzbski*, B.

Parameter-Efficient Transfer Learning for NLP N. Houlsby, A. Giurgiu*, S. Jastrzbski*, B.

Parameter-Efficient Transfer Learning for NLP N. Houlsby, A. Giurgiu*, S. Jastrzbski*, B. Morrone, Q. de Laroussilhe, A. Gesmundo, M. Attariyan, S. Gelly Imagine doing Transfer Learning for NLP Ingredients: A large pretrained model

739 views • 15 slides
Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive

Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive

Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio Kaito Fujii (UTokyo) & Shinsaku Sakaue (NTT) The 36th I nternational Conference on Machine Learning Jun. 12, 2019 Application: I n fl

955 views • 30 slides
AdaGeo: Adaptive Geometric Learning for Optimization and Sampling Gabriele Abbati 1 , Alessandra

AdaGeo: Adaptive Geometric Learning for Optimization and Sampling Gabriele Abbati 1 , Alessandra

AdaGeo: Adaptive Geometric Learning for Opti- mization and Sampling AdaGeo: Adaptive Geometric Learning for Optimization and Sampling Gabriele Abbati 1 , Alessandra Tosi 2 , Seth Flaxman 3 , Michael A Osborne 1 1 University of Oxford, 2

598 views • 30 slides
Data Mining II Optimization & Parameter Tuning Heiko Paulheim Why Parameter Tuning?

Data Mining II Optimization & Parameter Tuning Heiko Paulheim Why Parameter Tuning?

Data Mining II Optimization & Parameter Tuning Heiko Paulheim Why Parameter Tuning? What we have seen so far many learning algorithms for classification, regression, ... Many of those have parameters k and distance

797 views • 52 slides
Data Mining II Optimization & Parameter Tuning Heiko Paulheim Why Parameter Tuning?

Data Mining II Optimization & Parameter Tuning Heiko Paulheim Why Parameter Tuning?

Data Mining II Optimization & Parameter Tuning Heiko Paulheim Why Parameter Tuning? What we have seen so far many learning algorithms for classification, regression, ... Many of those have parameters k and distance

586 views • 54 slides
Probabilistic Graphical Models Probabilistic Graphical Models Parameter learning in Bayesian

Probabilistic Graphical Models Probabilistic Graphical Models Parameter learning in Bayesian

Probabilistic Graphical Models Probabilistic Graphical Models Parameter learning in Bayesian networks Siamak Ravanbakhsh Fall 2019 Learning objectives Learning objectives likelihood function and MLE role of the sufficient statistics MLE for

644 views • 60 slides
Model-Agnostic Meta-Learning Universality, Inductive Bias, and Weak Supervision Chelsea Finn

Model-Agnostic Meta-Learning Universality, Inductive Bias, and Weak Supervision Chelsea Finn

Model-Agnostic Meta-Learning Universality, Inductive Bias, and Weak Supervision Chelsea Finn Why Learn to Learn? - e ff ectively reuse data on other tasks - replace manual engineering of architecture, hyperparameters, etc. - learn to quickly

915 views • 30 slides
Understanding Git Nelson Elhage Anders Kaseorg Student Information Processing Board September

Understanding Git Nelson Elhage Anders Kaseorg Student Information Processing Board September

Understanding Git Nelson Elhage Anders Kaseorg Student Information Processing Board September 29, 2009 Nelson Elhage, Anders Kaseorg (SIPB) Understanding Git September 29, 2009 1 / 41 The Git model Outline The Git model 1 Using Git 2

974 views • 70 slides
CS885 Reinforcement Learning Module 3: July 5, 2020 Imitation Learning Torabi, F., Warnell, G.,

CS885 Reinforcement Learning Module 3: July 5, 2020 Imitation Learning Torabi, F., Warnell, G.,

CS885 Reinforcement Learning Module 3: July 5, 2020 Imitation Learning Torabi, F., Warnell, G., & Stone, P. (2018). Behavioral cloning from observation. In IJCAI (pp. 4950-4957). Ho, J., & Ermon, S. (2016). Generative adversarial

464 views • 14 slides
6hp http://www.ida.liu.se/~patla00/courses/BDA Teachers Lectures: Patrick Lambrix,

6hp http://www.ida.liu.se/~patla00/courses/BDA Teachers Lectures: Patrick Lambrix,

Big Data Analytics 6hp http://www.ida.liu.se/~patla00/courses/BDA Teachers Lectures: Patrick Lambrix, Christoph Kessler, Jose Pena, Valentina Ivanova, Labs: Zlatan Dragisic, Huanyu Li NSC: Rickard Armiento 2

2.32k views • 63 slides
ASIC and Custom in Nanometer Technologies David Chinnery Outline Introduction

ASIC and Custom in Nanometer Technologies David Chinnery Outline Introduction

High Performance and Low Power Design Techniques for ASIC and Custom in Nanometer Technologies David Chinnery Outline Introduction Microarchitecture Clock distribution, clock gating, and registers Logic style Cell design,

949 views • 40 slides
Posix-Free File Systems in the Cloud Jeff Chase Duke University Beyond Posix

Posix-Free File Systems in the Cloud Jeff Chase Duke University Beyond Posix

Posix-Free File Systems in the Cloud Jeff Chase Duke University Beyond Posix Filesystem Posix file system semantics? open(2) Hierarchical directories with aliasing Human-readable symbolic names Atomic ops on

599 views • 12 slides
Building a Robust Research Commons: Enhancing the Precompe99ve

Building a Robust Research Commons: Enhancing the Precompe99ve

2010 ITMAT International Symposium Philadelphia 26-27 October 2010 Building a Robust Research Commons: Enhancing the Precompe99ve Environment Tania Bubela School of Public Health

315 views • 30 slides
General Consent to Research Use of Biological Samples and Health Information Eiji Maruyama Kobe

General Consent to Research Use of Biological Samples and Health Information Eiji Maruyama Kobe

General Consent to Research Use of Biological Samples and Health Information Eiji Maruyama Kobe University, Japan Eiji Maruyama 2010WCML@Zagreb 1 Requirement of Informed Consent Obtaining informed consent from the subject or her/his legal

419 views • 17 slides

More recommend