Contextualized Robot Navigation

نویسندگان

  • David Vincent Lu
  • Chris Gill
  • Caitlin Kelleher
  • Bilge Mutlu
  • Annamaria Pileggi
  • David V. Lu
چکیده

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . x 1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 The Difficulty of Human-Robot Interaction . . . . . . . . . . . . . . . . . . . 1 1.2 “Robotic Motion” . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.2.1 Prior Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.3 Creating a Theory of Mind with Acting . . . . . . . . . . . . . . . . . . . . . 7 1.4 Robot Platforms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.4.1 The Robot Operating System ROS . . . . . . . . . . . . . . . . . . 9 1.4.2 Robots . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.4.3 Navigation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 2 Robots in Theatre . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.1 Robot Theatre Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.2 Physical Action . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.3 The Chinese Room and The Stage . . . . . . . . . . . . . . . . . . . . . . . . 17 2.4 The Ontology of Robot Theatre . . . . . . . . . . . . . . . . . . . . . . . . . 20 2.5 Practical Crossover . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 3 Theatre as an Implicit Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 3.1 Non-contextual Movement . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 3.1.1 Viewpoints: A Definition . . . . . . . . . . . . . . . . . . . . . . . . . 27 3.1.2 The Robot Acting Partner . . . . . . . . . . . . . . . . . . . . . . . . 30 3.1.3 Robots and Viewpoints . . . . . . . . . . . . . . . . . . . . . . . . . . 31 3.1.4 Transition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 3.2 Contextualized Movement . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 3.2.1 Composition of Forgiveness . . . . . . . . . . . . . . . . . . . . . . . 34 3.2.2 Performance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 3.2.3 Lessons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 3.3 Theatre as a Structure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 3.3.1 Three Act Structure for Navigation . . . . . . . . . . . . . . . . . . . 41 ii 3.4 Conclusions from Theatre . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 3.4.1 Collaboration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 4 The State of Contextualized Navigation . . . . . . . . . . . . . . . . . . . . 45 4.1 ROS Navigation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 4.1.1 Why ROS Navigation . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 4.1.2 Algorithmic Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46 4.2 Navigation in Practice . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 4.3 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 5 Towards More Efficient Navigation for Robots and Humans . . . . . . . . 54 5.1 Improving Navigation Interactions . . . . . . . . . . . . . . . . . . . . . . . . 54 5.2 System Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 5.2.1 Lasers for People Detection . . . . . . . . . . . . . . . . . . . . . . . 57 5.2.2 Gaze Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 5.2.3 Socially Aware Costmaps . . . . . . . . . . . . . . . . . . . . . . . . . 58 5.3 Experimental Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60 5.3.1 Procedure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60 5.3.2 Hypotheses . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63 5.4 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64 5.4.1 Statistical Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66 5.5 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67 6 Tuning Cost Functions for Social Navigation . . . . . . . . . . . . . . . . . 71 6.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 71 6.2 Mathematical Properties of Gaussian Obstacles . . . . . . . . . . . . . . . . 73 6.2.1 Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74 6.3 Results from Simulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76 6.4 Results using ROS Navigation . . . . . . . . . . . . . . . . . . . . . . . . . . 78 6.5 Tuning in Two Dimensions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 79 6.6 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 7 Layered Costmaps for Context-Sensitive Navigation . . . . . . . . . . . . 83 7.1 The Monolithic Costmap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83 7.2 Layered Costmaps Data Structure and Update Algorithm . . . . . . . . . . . 86 7.3 Benefits . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89 7.4 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90 7.4.1 Problems with the Previous Implementation . . . . . . . . . . . . . . 91 7.4.2 Layered Costmap Implementation . . . . . . . . . . . . . . . . . . . . 93 7.5 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 8 Layers in the Costmap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96 8.1 Standard Layers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A New Method of Mobile Robot Navigation: Shortest Null Space

In this paper, a new method was proposed for the navigation of a mobile robot in an unknown dynamic environment. The robot could detect only a limited radius of its surrounding with its sensors and it went on the shortest null space (SNS) toward the goal. In the case of no obstacle, SNS was a direct path from the robot to goal; however, in the presence of obstacles, SNS was a space around the r...

متن کامل

A New Method of Mobile Robot Navigation: Shortest Null Space

In this paper, a new method was proposed for the navigation of a mobile robot in an unknown dynamic environment. The robot could detect only a limited radius of its surrounding with its sensors and it went on the shortest null space (SNS) toward the goal. In the case of no obstacle, SNS was a direct path from the robot to goal; however, in the presence of obstacles, SNS was a space around the r...

متن کامل

Navigation of a Mobile Robot Using Virtual Potential Field and Artificial Neural Network

Mobile robot navigation is one of the basic problems in robotics. In this paper, a new approach is proposed for autonomous mobile robot navigation in an unknown environment. The proposed approach is based on learning virtual parallel paths that propel the mobile robot toward the track using a multi-layer, feed-forward neural network. For training, a human operator navigates the mobile robot in ...

متن کامل

Mobile Robot Navigation Error Handling Using an Extended Kalman Filter

Obviously navigation is one of the most complicated issues in mobile robots. Intelligent algorithms are often used for error handling in robot navigation. This Paper deals with the problem of Inertial Measurement Unit (IMU) error handling by using Extended Kalman Filter (EKF) as an Expert Algorithms. Our focus is put on the field of mobile robot navigation in the 2D environments. The main chall...

متن کامل

Mobile Robot Navigation Error Handling Using an Extended Kalman Filter

Obviously navigation is one of the most complicated issues in mobile robots. Intelligent algorithms are often used for error handling in robot navigation. This Paper deals with the problem of Inertial Measurement Unit (IMU) error handling by using Extended Kalman Filter (EKF) as an Expert Algorithms. Our focus is put on the field of mobile robot navigation in the 2D environments. The main chall...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015