RECORD
Cat-like Jumping and Landing of Legged Robots in Low-gravity Using Deep Reinforcement Learning
Robotics · Submitted 17 Jun 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The experimental results demonstrate that repetitive, controlled jumping and landing with natural agility is possible.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
In this article, we show that learned policies can be applied to solve legged locomotion control tasks with extensive flight phases, such as those encountered in space exploration. Using an off-the-shelf deep reinforcement learning algorithm, we trained a neural network to control a jumping quadruped robot while solely using its limbs for attitude control. We present tasks of increasing complexity leading to a combination of three-dimensional (re-)orientation and landing locomotion behaviors of a quadruped robot traversing simulated low-gravity celestial bodies. We show that our approach easily generalizes across these tasks and successfully trains policies for each case. Using sim-to-real transfer, we deploy trained policies in the real world on the SpaceBok robot placed on an experimental testbed designed for two-dimensional micro-gravity experiments. The experimental results demonstrate that repetitive, controlled jumping and landing with natural agility is possible.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | In this article, we show that learned policies can be applied to solve legged locomotion control tasks with extensive flight phases, such as those encountered in space exploration. | contribution 0.80 | 0.87 | 0.50 | asserted 1.00 |
| s1 | Using an off-the-shelf deep reinforcement learning algorithm, we trained a neural network to control a jumping quadruped robot while solely using its limbs for attitude control. | method 0.94 | 0.97 | 0.08 | asserted 1.00 |
| s2 | We present tasks of increasing complexity leading to a combination of three-dimensional (re-)orientation and landing locomotion behaviors of a quadruped robot traversing simulated low-gravity celestial bodies. | contribution 0.91 | 0.93 | 0.08 | asserted 0.97 |
| s3 | We show that our approach easily generalizes across these tasks and successfully trains policies for each case. | result 0.97 | 0.95 | 0.22 | asserted 1.00 |
| s4 | Using sim-to-real transfer, we deploy trained policies in the real world on the SpaceBok robot placed on an experimental testbed designed for two-dimensional micro-gravity experiments. | method 0.84 | 0.95 | 0.07 | asserted 1.00 |
| s5 | The experimental results demonstrate that repetitive, controlled jumping and landing with natural agility is possible. | result 0.89 | 0.95 | 0.67 | asserted 0.90 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
In this article, we show that learned policies can be applied to solve legged locomotion control tasks with extensive flight phases, such as those encountered in space exploration. Using an off-the-shelf deep reinforcement learning algorithm, we trained a neural network to control a jumping quadruped robot while solely using its limbs for attitude control. We present tasks of increasing complexity leading to a combination of three-dimensional (re-)orientation and landing locomotion behaviors of a quadruped robot traversing simulated low-gravity celestial bodies. We show that our approach easily generalizes across these tasks and successfully trains policies for each case. Using sim-to-real transfer, we deploy trained policies in the real world on the SpaceBok robot placed on an experimental testbed designed for two-dimensional micro-gravity experiments. The experimental results demonstrate that repetitive, controlled jumping and landing with natural agility is possible.
Human review
How the literature uses it
1 arXiv paper cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as support 1 paper
-
SpaceHopper's legs each have three active DOFs as this vastly outperforms legs with only two active DOFs in attitude control [ref] .
SpaceHopper: A Small-Scale Legged Robot for Exploring Low-Gravity Celestial Bodies · Leg Design · 1.00
What it cites · 6 sentences without a confident label
Uses the method or tool of 1 paper
-
The weights are learned using an off the shelf implementation [ref] of the Proximal Policy Optimization (PPO) algorithm [ref] .
Proximal Policy Optimization Algorithms · Policy optimization · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.