mlsanityData to 7 Oct 2026

Automatic Acquisition of a Repertoire of Diverse Grasping Trajectories through Behavior Shaping and Novelty Search

arXiv 2205.08189 ↗First posted 17 May 2022cs.RO cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Grasping a particular object may require a dedicated grasping movement that may also be specific to the robot end-effector. No generic and autonomous method does exist to generate these movements without making hypotheses on the robot or on the object. Learning methods could help to autonomously discover relevant grasping movements, but they face an important issue: grasping movements are so rare that a learning method based on exploration has little chance to ever observe an interesting movement, thus creating a bootstrap issue. We introduce an approach to generate diverse grasping movements in order to solve this problem. The movements are generated in simulation, for particular object positions. We test it on several simulated robots: Baxter, Pepper and a Kuka Iiwa arm. Although we show that generated movements actually work on a real Baxter robot, the aim is to use this method to create a large dataset to bootstrap deep learning methods.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 17 May 2022.

Builds on

22 of 37 references.

References · 22

  1. 2016OpenAI Gymcited by 1,684
  2. 2015Illuminating search spaces by mapping elitescited by 406
  3. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  4. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 286
  5. 2017Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metricscited by 259
  6. 2015Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hourscited by 208
  7. 2014Robots that can adapt like animalscited by 203
  8. 2013Deep Learning for Detecting Robotic Graspscited by 114
  9. 2017Quality and Diversity Optimization: A Unifying Modular Frameworkcited by 111
  10. 2013Data-Driven Grasp Synthesis - A Surveycited by 104
  11. 2019Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrationscited by 104
  12. 2018Jacquard: A Large Scale Dataset for Robotic Grasp Detectioncited by 86
10 more
  1. 2017Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learningcited by 79
  2. 2018Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitationcited by 76
  3. 2016Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithmcited by 65
  4. 2019Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptorscited by 57
  5. 2019Unsupervised Learning and Exploration of Reachable Outcome Spacecited by 23
  6. 2020Model-Based Quality-Diversity Search for Efficient Robot Learningcited by 14
  7. 2019From exploration to control: learning object manipulation skills through novelty search and local adaptationcited by 12
  8. 2020Novelty Search makes Evolvability Inevitablecited by 6
  9. 2021Ensemble Feature Extraction for Multi-Container Quality-Diversity Algorithmscited by 3
  10. 2019qiBullet, a Bullet-based simulator for the Pepper and NAO robotscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 5; 2024: 1.

9 papers.

  1. 2023pyribs: A Bare-Bones Python Library for Quality Diversity Optimizationcited by 29
  2. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  3. 2023Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learningcited by 20
  4. 2024CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectoriescited by 11
  5. 2022Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealingcited by 10
  6. 2023Domain Randomization for Sim2real Transfer of Automatically Generated Grasping Datasetscited by 8
  7. 2023Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Roboticscited by 6
  8. 2022E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectoriescited by 1
  9. 2022Random Actions vs Random Policies: Bootstrapping Model-Based Direct Policy Searchcited by 0