mlsanityData to 14 Oct 2026

Latent Representations for Visual Proprioception in Inexpensive Robots

arXiv 2504.14634 ↗First posted 20 Apr 2025cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Robotic manipulation requires explicit or implicit knowledge of the robot's joint positions. Precise proprioception is standard in high-quality industrial robots but is often unavailable in inexpensive robots operating in unstructured environments. In this paper, we ask: to what extent can a fast, single-pass regression architecture perform visual proprioception from a single external camera image, available even in the simplest manipulation settings? We explore several latent representations, including CNNs, VAEs, ViTs, and bags of uncalibrated fiducial markers, using fine-tuning techniques adapted to the limited data available. We evaluate the achievable accuracy through experiments on an inexpensive 6-DoF robot.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 25 references that are in the map. First posted on arXiv 20 Apr 2025.

Builds on

15 of 25 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  5. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
  6. 2019Camera-to-Robot Pose Estimation from a Single Imagecited by 48
  7. 2021Single-view robot pose and joint angle estimation via render & comparecited by 33
  8. 2020Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose Estimationcited by 25
  9. 2023Markerless Camera-to-Robot Pose Estimation via Self-supervised Sim-to-Real Transfercited by 24
  10. 2018CRAVES: Controlling Robotic Arm with a Vision-based Economic Systemcited by 18
  11. 2024RoboKeyGen: Robot Pose and Joint Angles Estimation via Diffusion-based 3D Keypoint Generationcited by 10
  12. 2024Real-time Holistic Robot Pose Estimation with Unknown Statescited by 9
3 more
  1. 2022Semi-Perspective Decoupled Heatmaps for 3D Robot Pose Estimation from Depth Mapscited by 6
  2. 2024Precision-Focused Reinforcement Learning Model for Robotic Object Pushingcited by 5
  3. 2019Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in Cluttercited by 2

Built on by

Not cited yet.