Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry

  title={Tactile-RL for Insertion: Generalization to Objects of Unknown Geometry},
  author={Siyuan Dong and Devesh K. Jha and Diego Romeres and Sangwoon Kim and Daniel Nikovski and Alberto Rodriguez},
  journal={2021 IEEE International Conference on Robotics and Automation (ICRA)},
Object insertion is a classic contact-rich manipulation task. The task remains challenging, especially when considering general objects of unknown geometry, which significantly limits the ability to understand the contact configuration between the object and the environment. We study the problem of aligning the object and environment with a tactile-based feedback insertion policy. The insertion process is modeled as an episodic policy that iterates between insertion attempts followed by pose… 

Figures and Tables from this paper

Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertion
A method that actively estimates the location of contact between a grasped rigid object and its environment, and uses this as input to a peg-in-hole insertion policy, and an objectagnostic insertion policy that learns to make use of the series of contact estimates to guide the insertion is proposed.
Imitation and Supervised Learning of Compliance for Robotic Assembly
A learning-based compliance controller for assembly operations for industrial robots that can correct various contact configurations caused by misalignment between the assembled parts in a PiH task, achieving high success rate during insertion.
PatchGraph: In-hand tactile tracking with learned surface normals
This work addresses the problem of tracking 3D object poses from touch during in-hand manipulations using vision-based tactile sensors that provide high-dimensional tactile image measurements at the point of contact using a novel two-stage approach.
SEED: Series Elastic End Effectors in 6D for Visuotactile Tool Use
We propose the framework of Series Elastic End Effectors in 6D (SEED), which combines a spatially compliant element with visuotactile sensing to grasp and manipulate tools in the wild. Our framework
PYROBOCOP : Python-based Robotic Control & Optimization Package for Manipulation and Collision Avoidance
PYROBOCOP provides automatic reformulation of the complementarity constraints that enables NLP solvers to perform optimization of robotic systems and provides comparisons with other open source optimization packages like CasADi and Pyomo.
Electric Vehicle Automatic Charging System Based on Vision-force Fusion
A complete automatic charging system based on vision-force fusion, which includes perception, planning and control for robot manipulations of the system is introduced.
FabricFlowNet: Bimanual Cloth Manipulation with a Flow-based Policy
FabricFlowNet is introduced, a cloth manipulation policy that leverages flow as both an input and as an action representation to improve performance and generalizes when trained on a single square cloth to other cloth shapes, such as T-shirts and rectangular cloths.


Tactile-Based Insertion for Dense Box-Packing
An insertion strategy that leverages tactile sensing to safely probe the box with the grasped object while monitoring incipient slip to maintain a stable grasp on the object is proposed and its ability to generalize to novel objects makes it a good fit for box packing in warehouse automation.
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
This work uses self-supervision to learn a compact and multimodal representation of sensory inputs, which can then be used to improve the sample efficiency of the policy learning of deep reinforcement learning algorithms.
Realtime State Estimation with Tactile and Visual Sensing for Inserting a Suction-held Object
This paper focuses on the application of inserting an object picked by a suction cup into a tight space, a key technology for robotic packaging, and proposes a framework that fuses tactile and visual sensing.
Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks
This paper investigates the merits of multiple sensor modalities such as vision, force/torque sensors, and proprioception when combined to learn a controller for real world assembly operation tasks using LfD techniques, and proposes a multi-step-ahead loss function to improve the performance of the behavioral cloning method.
Learning contact-rich manipulation skills with guided policy search
This paper extends a recently developed policy search method and uses it to learn a range of dynamic manipulation behaviors with highly general policy representations, without using known models or example demonstrations, and shows that this method can acquire fast, fluent behaviors after only minutes of interaction time.
Extrinsic Contact Sensing with Relative-Motion Tracking from Distributed Tactile Measurements
The theoretical basis for the value of distributed tactile sensing in contrast to aggregated force/torque measurements is discussed and an estimation framework for localizing environmental contacts with potential impact in contact-rich manipulation scenarios such as assembling or packing is provided.
Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards
This paper considers a variety of difficult industrial insertion tasks with visual inputs and different natural reward specifications, namely sparse rewards and goal images and shows that methods that combine RL with prior information can solve these tasks from a reasonable amount of real-world interaction.
Deep Reinforcement Learning for Robotic Assembly of Mixed Deformable and Rigid Objects
Force-torque measurements from a robot arm wrist sensor are integrated two-fold; they are integrated into the policy learning process and they are exploited in an admittance controller that is coupled to the neural network that enables robot learning of contact-rich assembly tasks without explicit joint torque control or passive mechanical compliance.
A comparative study of contact models for contact-aware state estimation
Four particle filters are evaluated based upon four probabilistic state transition models generated from a deterministic multibody dynamics models with rigid or compliant contacts, each of which is augmented by one of two different noise models.
Maintaining Grasps within Slipping Bounds by Monitoring Incipient Slip
An approach to detect incipient slip, i.e. predict slip, by using a high-resolution vision-based tactile sensor, GelSlim, which dynamically captures the tactile imprints of the grasped object and their changes with a soft gel pad is proposed.