Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining

• URL: http://arxiv.org/abs/2609.12721v1
• Date: Fri, 11 Sep 2026 11:19:06 GMT
• Title: Improving Imitation Learning Efficiency for Manipulation through Geometric Prior Pretraining
• Abstract summary: In this study, we construct a geometric visual pretraining dataset in which each scene contains only a plane, an object, and a hand.<n>We evaluate this geometric prior using ACT on three simulated robots across five manipulation tasks each, as well as on three real-world robot tasks.
• Score: 21.64711515041526
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Applying an imitation learning policy to a new manipulation task usually requires collecting new demonstrations and retraining the model, which makes sample efficiency a practical concern. Pretraining on large-scale robot datasets is effective in this respect, but such datasets are costly to collect and train on, while data augmentation techniques typically require a new round of data generation and retraining for each task. A complementary question is what useful prior can be provided to a policy at negligible cost before any task-specific data are collected. In this study, we construct a geometric visual pretraining dataset in which each scene contains only a plane, an object, and a hand, and trajectories are generated automatically. The scenes contain neither textures nor backgrounds; pretraining primarily exposes the policy to the geometric relationship between the hand and the object. Furthermore, representing the hand as a cube avoids tailoring the dataset to a specific robot morphology. We evaluate this geometric prior using ACT on three simulated robots across five manipulation tasks each, as well as on three real-world robot tasks. Across many of these robot--task combinations, fine-tuning from the geometric prior achieves higher success rates in the early stages of training than training from scratch while using only a small number of task demonstrations. These results suggest that even highly simplified geometric scenes can provide a useful initialization that transfers across robots and to real-world tasks when task data are limited.

Related papers

• Using Temperature Sampling to Effectively Train Robot Learning Policies on Imbalanced Datasets [3.342232437547785]
  Many datasets of robotic tasks are substantially imbalanced in terms of the physical robotic actions they represent.<n>We propose a simple sampling strategy for policy training that mitigates this imbalance.<n>Our results show substantial improvements on low-resource tasks compared to prior state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-10-22T08:48:55Z)
• Constraint-Preserving Data Generation for Visuomotor Policy Learning [46.576295441652405]
  We use a single expert trajectory to generate robot demonstrations containing novel object geometries and poses.<n>These generated demonstrations are used to train closed-loop visuomotor policies that transfer zero-shot to the real world.
  arXiv  Detail & Related papers  (2025-08-05T22:20:02Z)
• Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use [20.644849892016122]
  We propose a framework that transfers tool-use knowledge from humans to robots.<n>We demonstrate our framework's effectiveness across a diverse suite of tool-use tasks.<n>Our method achieves a 71% improvement in task success over teleoperation-based diffusion policies.
  arXiv  Detail & Related papers  (2025-04-06T20:40:19Z)
• STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning [8.860366821983211]
  STRAP is a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion.<n>This work proposes STRAP, a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion.
  arXiv  Detail & Related papers  (2024-12-19T18:54:06Z)
• Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers [41.069074375686164]
  We propose Heterogeneous Pre-trained Transformers (HPT), which pre-train a trunk of a policy neural network to learn a task and embodiment shared representation. We conduct experiments to investigate the scaling behaviors of training objectives, to the extent of 52 datasets. HPTs outperform several baselines and enhance the fine-tuned policy performance by over 20% on unseen tasks.
  arXiv  Detail & Related papers  (2024-09-30T17:39:41Z)
• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets [122.85598648289789]
  We study how multi-domain and multi-task datasets can improve the learning of new tasks in new environments. We also find that data for only a few tasks in a new domain can bridge the domain gap and make it possible for a robot to perform a variety of prior tasks that were only seen in other domains.
  arXiv  Detail & Related papers  (2021-09-27T23:42:12Z)
• A Framework for Efficient Robotic Manipulation [79.10407063260473]
  We show that a single robotic arm can learn sparse-reward manipulation policies from pixels. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels.
  arXiv  Detail & Related papers  (2020-12-14T22:18:39Z)
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning [79.32403825036792]
  We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials. We show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors.
  arXiv  Detail & Related papers  (2020-11-19T18:47:40Z)
• COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning [78.13740204156858]
  We show that we can reuse prior data to extend new skills simply through dynamic programming. We demonstrate the effectiveness of our approach by chaining together several behaviors seen in prior datasets for solving a new task. We train our policies in an end-to-end fashion, mapping high-dimensional image observations to low-level robot control commands.
  arXiv  Detail & Related papers  (2020-10-27T17:57:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.