Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Tactile-based Interactive Motion Planner for Robots in Unknown Cluttered Environments

Chengjin Wang, Yanmin Zhou, Zheng Yan, Feng Luan, Runjie Shen, Hongrui Sang, Zhipeng Wang, Bin He

Abstract

In unknown cluttered environments with densely stacked objects, the free-motion space is extremely barren, posing significant challenges to motion planners. Collision-free planning methods often suffer from catastrophic failures due to unexpected collisions and motion obstructions. To address this issue, this paper proposes an interactive motion planning framework (I-MP), based on a perception-motion loop. This framework empowers robots to autonomously model and reason about contact models, which in turn enables safe expansion of the free-motion space. Specifically, the robot utilizes multimodal tactile perception to acquire stimulus-response signal pairs. This enables real-time identification of objects' mechanical properties and the subsequent construction of contact models. These models are integrated as computational constraints into a reactive planner. Based on fixed-point theorems, the planner computes the spatial state toward the target in real time, thus avoiding the computational burden associated with extrapolating on high-dimensional interaction models. Furthermore, high-dimensional interaction features are linearly superposed in Cartesian space in the form of energy, and the controller achieves trajectory tracking by solving the energy gradient from the current state to the planned state. The experimental results showed that at cruising speeds ranging from 0.01 to 0.07 $m/s$, the robot's initial contact force with objects remained stable at 1.0 +- 0.7 N. In the cabinet scenario test where collision-free trajectories were unavailable, I-MP expanded the free motion space by 37.5 % through active interaction, successfully completing the environmental exploration task.

A Tactile-based Interactive Motion Planner for Robots in Unknown Cluttered Environments

Abstract

In unknown cluttered environments with densely stacked objects, the free-motion space is extremely barren, posing significant challenges to motion planners. Collision-free planning methods often suffer from catastrophic failures due to unexpected collisions and motion obstructions. To address this issue, this paper proposes an interactive motion planning framework (I-MP), based on a perception-motion loop. This framework empowers robots to autonomously model and reason about contact models, which in turn enables safe expansion of the free-motion space. Specifically, the robot utilizes multimodal tactile perception to acquire stimulus-response signal pairs. This enables real-time identification of objects' mechanical properties and the subsequent construction of contact models. These models are integrated as computational constraints into a reactive planner. Based on fixed-point theorems, the planner computes the spatial state toward the target in real time, thus avoiding the computational burden associated with extrapolating on high-dimensional interaction models. Furthermore, high-dimensional interaction features are linearly superposed in Cartesian space in the form of energy, and the controller achieves trajectory tracking by solving the energy gradient from the current state to the planned state. The experimental results showed that at cruising speeds ranging from 0.01 to 0.07 , the robot's initial contact force with objects remained stable at 1.0 +- 0.7 N. In the cabinet scenario test where collision-free trajectories were unavailable, I-MP expanded the free motion space by 37.5 % through active interaction, successfully completing the environmental exploration task.

Paper Structure

This paper contains 19 sections, 40 equations, 10 figures, 1 table.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Proposed Solution
  4. Outline
  5. Problem statement and notation
  6. Interactive Motion Planning Problem
  7. Autonomous Contact Modeling Problem
  8. Methodology
  9. Environment Understanding
  10. Contact Modeling and Environment Representation
  11. Interactive Motion Planner
  12. Low Level Control
  13. Experimental Platform
  14. Statistical Performance of I-MP
  15. Motion-Control Continuity
  16. ...and 4 more sections

Figures (10)

  • Figure 1: Overview of the I-MP Framework. (A) Overview of the motion planning architecture. (B) Core I-MP components. The I-MP consists of environment understanding (EU), reactive planner (RP), and low-level controller (LC) as its modules.
  • Figure 2: Simulated robot interactions with operable objects. (A): The trajectory and planned motion variables of the robot that traverses three target points. (B): Joint torques and end-effector velocity of the robot. (C): Interaction forces and end-effector velocity during robot interaction with objects.
  • Figure 3: Hardware tests where the robot interacts with varying object types: fixed wood (A), fixed steel (B), movable foam (C), fixed elastic balloons (D), movable wood (E), movable steel (F).
  • Figure 4: Design of test scenarios and elucidation of the task difficulty.
  • Figure 5: Baseline comparison of I-MP in success rate and path cost. (A) Comparison of success rates between I-MP and probability-, model-, and simulation-based planning methods. (B) Statistical differences between the I-MP-driven robotic motion paths and baseline method paths.
  • ...and 5 more figures