TBM3 - “Catering for Granny Annie’s Comfort”

From RoCKIn Wiki
Revision as of 17:14, 10 April 2015 by Rockinadmin (Talk | contribs) (Created page with "== Robot setup == See Preparing the robot for task benchmarks. == Comfort items == *Comfort Items that Granny Annie may...")

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Robot setup

See Preparing the robot for task benchmarks.

Comfort items

  • Comfort Items that Granny Annie may ask the robot to bring:*
  • Cardboard box with RoCKIn logo, size 120x140x40 [mm];
  • Large transparent blue plastic glass with 3 extra spares (IKEA Code: 902.649.68);
  • Pair of normal glasses.

See pictures bellow.


  • Likely locations:*

|_.Objects |_.Localization |_.Likelihood | |/2.Cardboard box | On the dining table | 60 | | On the kitchen table | 40 | |/2.Cup | On the kitchen counter | 60 | | On the kitchen table | 40 | |/2.Reading Glasses| On the bedside table | 75 | | On the center table | 25 |


!box.png! !cup.jpg! !glasses.png!

Protocol to communicate with the tablet App used for Granny Annie to interact with the robot

Included as part of the RSBB client libraries, see RoCKIn@Home Referee, Scoring and Benchmarking Box.

Software module to interact with home automation controller networked device

Included as part of the RSBB client libraries, see RoCKIn@Home Referee, Scoring and Benchmarking Box.


List of variables to be logged

The robot is required to log any sensor data used to perform the benchmark (e.g., audio signals, robot pose, sensorial data). The modalities for this are explained by "this document":http://rm.isr.ist.utl.pt/attachments/622/robot_data.txt. Only relevant data is expected to be logged (i.e., the pointcloud used to classify an object, more than one if an algorithm requiring multiple pointclouds is used). There are no restriction about the framerate: data can be saved, for the relevant parts of the benchmark, at the rate they are acquired or produced. The log may be a rosbag or the corresponding YAML representation, as specified in document:"RoCKIn YAML Data File Specification".

The following are expected ROS topic names and corresponding data types:

  • audio [@audio_common_msgs/AudioData@]: the audio of the conversation between Annie and the robot
  • command [@std_msgs/String@]: the final command produced during the natural language analysis process
  • pose2d [@geometry_msgs/Pose2D@]: 2D pose of the robot while moving in the environment, as perceived by the robot
  • pose [@geometry_msgs/Pose@]: 3D pose of the robot while moving in the environment, as perceived by the robot (if available)
  • image [@sensor_msgs/Image@]: sensorial data used to recognize the object to be operated
  • pointcloud [@sensor_msgs/PointCloud2@]: sensorial data used to recognize the object to be operated

+Important!+ Calibration parameters for cameras must be saved. This must be done also for other sensors (e.g., Kinect) that require calibration, if a calibration procedure has been applied instead of using the default values (e.g., those provided by OpenNI).

Sentences and lexicon examples

Examples of sentences that Granny Annie will utter during this benchmark are reported in this section. A zip file containing the sentences and the related lexicon can be downloaded "here":http://rm.isr.ist.utl.pt/attachments/638/TBM3_examples.zip. The content of the .zip file is explained in the following:

  • *sentences*: the example sentences
  • *verbs*: all the verb used in the example sentences
  • *nouns*: all the single nouns used in the example sentences (not the composed ones, as "dining table". In this case two single nouns composing the noun are reported, e.g. "dining" and "table")
  • *prepositions*: all the prepositions used in the example sentences
  • *adverbs*: all the adverbs used in the example sentences
  • *personal_pronouns*: personal pronouns used in the example sentences, as "it" or "me"
  • *others*: other words not included in the previous category

In addition to the sentences and the lexicon, we provide also the audio version of the examples. These files have been recorded by the same person that will play the role of Granny Annie, and can be downloaded "here":http://rm.isr.ist.utl.pt/attachments/606/Granny_Annie_Recordings.zip.