FOIA: Humanoids (robots) for Lunar and Planetary Surface Operations

HUMANIODS_FOR_L UNAR_SURFACE_OPERATIONS.pdf
Humanoids (robots) for Lunar and Planetary Surface Operations
The report "Humanoids for Lunar and Planetary Surface Operations" discusses the probable need for robots at lunar bases.
Document date: 2005-12-31
Department: Jet Propulsion Laboratory
Author: Adrian Stoica, Didier Keymeulen, Steven Sandoval, Jiajing Xu
Document type: report
pages: 6


Archivist's Notes: A good quality text document.

This JPL document outlines the steps and methods to teach a fully functional multipurpose robot to work independently in a space environment and to assist humans in colonization needs such as building , repair and exploration. While acknowledging other robotic forms, the authors express the opinion that for space/colonization purposes, the human form is best suited.

A large portion of the document is related to the teaching method envisioned by the authors. They seem to feel that observing and interacting with humans will be the most productive avenue for the robots to learn.

There is some mention of a project,Humanoid Open Architecture Platform, Second generation (HOAP-2) that has already, at the time of this document, made some progress in certain areas. HOAP-2 can perform certain basic actions either autonomously using it's own computer, or remotely controlled wirelessly from a "command environment" running a real time Linux system. (Eat your heart out Microsoft!)

Overall this is a concept document aiming at developing teaching methods to have a robotic "helper/colonist" in place and functional by 2023. How far this plan has progressed since the time of this outline in 2004 is unknown.

reply to post by NGC2736


Abstract - This paper presents a vision of humanoid robots as human’s key partners in future space exploration, in particular for construction, maintenance/repair and operation of lunar/planetary habitats, bases and settlements. It integrates this vision with the recent plans ,for human and robotic exploration, aligning a set of milestones for operational capability of humanoids with the schedule for the next decades and development spirals in the Project Constellation.
These milestones relate to a set of incremental challenges, for the solving of which new humanoid technologies are needed. A system of systems integrative approach that would lead to readiness of cooperating humanoid crews is sketched.
Robot fostering, training/education techniques, and improved cognitive/sensory/motor development techniques are considered essential elements for achieving intelligent humanoids. A pilot project in this direction is outlined.


I found several parts of this document very interesting:

PDF page 1:
The exploration plan starts with human returns to Moon as a stepping stone
for future missions to Mars.
Spiral 1 addresses the first crewed CEV flight in LEO, by
2014 (more recent plan target an earlier date, perhaps as
early as 2011); Spiral 2, the first human lunar return, by
2020; Spiral 3, the Moon as a testbed for Mars, by -2023;
Spiral 4, the deployment of launch vehicle for Mars
exploration, by -2026; Spiral 5, the development of
interplanetary transportation vehicle and support
infrastructure that could take humans to Mars and beyond,
by -2029; and Spiral 6, the deployment of transformational
new systems for surface access and operations to enable human excursions
to the surface of Mars, after 2030.

PDF page 2:
Recent studies also show additional advantages of humanoids, summarized here after:
a) Human interaction with robots is easier if the robots
are humanoid;
b) Robot acceptance by humans is easier for humanoid
shape;
c) Efficiency of teaching/programming a robot is highest with humanoids.
In particular related to the later aspect, one should stress here that although mobility, flexibility and adaptation to human environments offered by human shape is a convenient advantage, the key reason for preferring humanoids is their optimal shape for being taught by humans and learning from humans, considered the most effective ways to develop cognitive and perceptual / motor skills for truly intelligent, cognitive
robots.



PDF page 3:
The MIT pioneering work on COG and other anthropomorphic robots is significant, in particular efforts in the last few years from Cynthia Breazeal and collaborators exploring human-oriented interactions with
these robots. On the other hand, there is much more out there in other research fields that can be ported and integrated to the humanoid body to provide a powerful platform to develop it to operational levels.
Examples of several technologies available, yet not well incorporated in humanoids include: lanauage technologies. including voice recognition, speech to text and voice synthesis, which are sufficiently developed to allow simple interaction with the robot in spoken English (simple Japanese exists in some research robots); face/gesture recognition, sufficiently developed to allow robots to read “moods” of instructor, follow cues, etc (as prototyped e.g. on some MIT robots);

PDF page 6:
Plan for 2006-2009:full-size demonstration of a realistic structure assembly in lab. A natural continuation of this effort after a successful demonstration of the 2005 demo phase would be an effort to demonstrate a humanoid team; each human-size robot able to walk inside buildings, transport objects (select/lift/transport/place in right position), climb
ladders/scaffolds/tables and assemble modular components.

Conclusions
Humanoids could play a key role in lunar and planetary surface missions, starting with construction of habitats. The appropriate beginning of insertion of humanoid technology into missions is 2023 - 2030 timeframe. To be ready in time we need to start now. Initial results in using a small-scale humanoid to perform tasks.

I was disappointed in the pictures in the document, so I looked around and found this video on the HOAP-2 humanoid robot that is pretty impressive.



It's called HOAP-2 SUMO and there are other videos available on YouTube if your interested.