Corpus ID: 88503668

Neural Graph Evolution: Towards Efficient Automatic Robot Design

@article{Wang2019NeuralGE,
  title={Neural Graph Evolution: Towards Efficient Automatic Robot Design},
  author={Tingwu Wang and Yuhao Zhou and Sanja Fidler and Jimmy Ba},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.05370}
}
Despite the recent successes in robotic locomotion control, the design of robot relies heavily on human engineering. [...] Key Method Different from previous approaches, NGE uses graph neural networks to parameterize the control policies, which reduces evaluation cost on new candidates with the help of skill transfer from previously evaluated designs.Expand
What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks
TLDR
Evaluations in simulation show that the new method can co-adapt agents within such a limited number of production cycles by efficiently combining design optimization with offline reinforcement learning, that it allows for the direct application to real-world co- Adaptation tasks in future work. Expand
Multi-Objective Graph Heuristic Search for Terrestrial Robot Design
TLDR
This work introduces a new universal, multiobjective heuristic function based on graph neural networks that is able to effectively leverage learned information between different task trade-offs and demonstrates that this approach quantitatively and qualitatively outperforms other techniques. Expand
Learning Robot Structure and Motion Embeddings using Graph Neural Networks
  • J. Taery Kim, Jeongeun Park, Sungjoon Choi, Sehoon Ha
  • Computer Science
  • ArXiv
  • 2021
TLDR
A learning framework to find the representation of a robot’s kinematic structure and motion embedding spaces using graph neural networks (GNN) and exploits the tree structure of the robot to train appropriate embeddings to the given robot data. Expand
The Effects of Learning in Morphologically Evolving Robot Systems
TLDR
A system where modular robots can create offspring that inherit the bodies of parents by recombination and mutation is set up, and it is shown that the evolution plus learning method does not only lead to a higher fitness level, but also to more morphologically evolving robots. Expand
Task-Agnostic Morphology Evolution
TLDR
Without any task or reward specification, TAME evolves morphologies by only applying randomly sampled action primitives on a population of agents using an information-theoretic objective that efficiently ranks agents by their ability to reach diverse states in the environment and the causality of their actions. Expand
Neural fidelity warping for efficient robot morphology design
TLDR
The proposed fidelity warping mechanism can learn representations of learning epochs and tasks to model non-stationary covariances between continuous fidelity evaluations which prove challenging for off-the-shelf stationary kernels. Expand
Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
TLDR
This work develops a novel Bayesian Optimization algorithm that efficiently co-designs the morphology and grasping skills through learned latent-space representations and discovers robust and cost-efficient hand morphologies for grasping novel objects. Expand
Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
TLDR
The Evolving Graphical Planner (EGP) is introduced, a model that performs global planning for navigation based on raw sensory input that dynamically constructs a graphical representation, generalizes the action space to allow for more flexible decision making, and performs efficient planning on a proxy graph representation. Expand
Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations
TLDR
A learning-in-the-loop co-optimization algorithm in which a latent state representation is learned as the robot figures out how to solve the task, which is more robust and faster converging than the dynamics-oblivious baseline. Expand
One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control
TLDR
It is shown that a single modular policy can successfully generate locomotion behaviors for several planar agents with different skeletal structures such as monopod hoppers, quadrupeds, bipeds, and generalize to variants not seen during training -- a process that would normally require training and manual hyperparameter tuning for each morphology. Expand
...
1
2
...

References

SHOWING 1-10 OF 40 REFERENCES
Efficient Neural Architecture Search via Parameter Sharing
TLDR
Efficient Neural Architecture Search is a fast and inexpensive approach for automatic model design that establishes a new state-of-the-art among all methods without post-training processing and delivers strong empirical performances using much fewer GPU-hours. Expand
Memetic Compact Differential Evolution for Cartesian Robot Control
TLDR
The proposed Memetic compact Differential Evolution (McDE) algorithm has been tested and compared with other algorithms belonging to the same category for a real-world industrial application and has proven to considerably outperform other compact algorithms representing the current state-of-the-art in this sub-field of computational intelligence. Expand
Bayesian optimization for learning gaits under uncertainty
TLDR
Bayesian optimization, a model-based approach to black-box optimization under uncertainty, is evaluated on both simulated problems and real robots, demonstrating that Bayesian optimization is particularly suited for robotic applications, where it is crucial to find a good set of gait parameters in a small number of experiments. Expand
Hierarchical Representations for Efficient Architecture Search
TLDR
This work efficiently discovers architectures that outperform a large number of manually designed models for image classification, obtaining top-1 error of 3.6% on CIFAR-10 and 20.3% when transferred to ImageNet, which is competitive with the best existing neural architecture search approaches. Expand
Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding
TLDR
The ability of generative soft-voxel systems to scale towards evolving a large diversity of complex, natural, multi-material creatures is suggested. Expand
Evolving Neural Networks through Augmenting Topologies
TLDR
A method is presented, NeuroEvolution of Augmenting Topologies (NEAT), which outperforms the best fixed-topology method on a challenging benchmark reinforcement learning task and shows how it is possible for evolution to both optimize and complexify solutions simultaneously. Expand
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
TLDR
This paper proposes a new algorithm called probabilistic ensembles with trajectory sampling (PETS) that combines uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation, which matches the asymptotic performance of model-free algorithms on several challenging benchmark tasks, while requiring significantly fewer samples. Expand
NerveNet: Learning Structured Policy with Graph Neural Networks
TLDR
NerveNet is proposed to explicitly model the structure of an agent, which naturally takes the form of a graph, and is demonstrated to be significantly more transferable and generalizable than policies learned by other models and are able to transfer even in a zero-shot setting. Expand
An evolutionary system for automatic robot design
  • Wei-Po Lee
  • Computer Science
  • SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218)
  • 1998
TLDR
The paper examines the way to use evolutionary techniques to synthesize robots automatically and shows that the system can be used to reduce the load of a robot programmer. Expand
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
TLDR
It is demonstrated that neural network dynamics models can in fact be combined with model predictive control (MPC) to achieve excellent sample complexity in a model-based reinforcement learning algorithm, producing stable and plausible gaits that accomplish various complex locomotion tasks. Expand
...
1
2
3
4
...