Machine learning–driven self-discovery of the robot body morphology
Problem
Robot morphology is typically assumed known and calibrated via external measuring devices; whether a robot can learn elements of its own body morphology by itself was largely unexplored.
Why it matters
Self-discovery of body morphology could remove dependence on external measuring devices and prior knowledge.
What the AI did
Proposed proprioceptive information graphs (π-graphs), a mutual information-based representation of proprioceptive signals, used to infer fundamental kinematic elements of the robot's structure.
Results
π-graph analysis led to inference of two fundamental elements of the robot's morphology; abstract truncated before further details.
Impact
Demonstrates a robot can infer elements of its own morphology from unorganized proprioceptive signals alone.
Record
| Venue | Science Robotics |
|---|---|
| Published | 2023 |
| Work type | article |
| Authors | Fernando Díaz Ledezma, Sami Haddadin |
| Citations | 18 (OpenAlex, at import time) |
| References | 58 |
| Model or method | π-graphs (mutual information-based) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1126/scirobotics.adh0972 |
| Open access | closed |
| Keywords | proprioception, morphology, mutual information, π-graphs, self-modeling, kinematics |
Importance rating
incremental / niche
Self-discovery of robot morphology removes dependence on external measuring devices; abstract frames it as an unexplored research question with no stated application scale.
More in Robotics & Autonomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Autonomous robotic laparoscopic surgery for intestinal anastomosis | 2022 | 384 |
7
|
| 2 | Solving Rubik's Cube with a Robot Hand | 2019 | 569 |
6
|
| 3 | PaLM-E: An Embodied Multimodal Language Model | 2023 | 346 |
6
|
| 4 | Assistive Navigation Using Deep Reinforcement Learning Guiding Robot With UWB/Voice Beacons and Semantic Feedbacks for Blind and Visually Impaired People | 2021 | 48 |
6
|
| 5 | Towards Deep Radar Perception for Autonomous Driving: Datasets, Methods, and Challenges | 2022 | 154 |
6
|