Robot Surface Acoustic Sensing for Blind-Spot-Free Collision Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing collision avoidance systems for robotic manipulators face challenges in accurately detecting obstacles in cluttered environments, particularly at short ranges, due to limitations of camera-based methods and directional proximity sensors, which are expensive, require multiple sensors, and have blind spots.

Innovation Solution

A system using piezoelectric elements to generate and receive acoustic waves, filtered through band-pass and linear time-invariant filters, and processed by a neural network for obstacle detection, enabling full surface proximity detection with a single sensor pair.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If camera-based object recognition or 3D shape reconstruction is used for collision avoidance, then obstacle detection capability is improved, but detection accuracy at short ranges (less than 10 cm) deteriorates and the system becomes sensitive to occlusions and poor light conditions

Engineering Contradiction:
Improveobstacle detection accuracyVSAvoiddetection reliability in various conditions
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent replaces camera-based optical detection with acoustic wave-based detection using piezoelectric elements. This substitution enables reliable short-range detection (less than 10 cm) by using acoustic waves that are not affected by occlusions, lighting conditions, or transparency of objects, directly resolving the limitations of camera-based systems

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent utilizes mechanical vibration through piezoelectric elements that generate and detect acoustic waves. The piezoelectric elements vibrate to emit acoustic waves and detect vibrations caused by obstacles, providing reliable detection at short ranges where camera-based methods fail

Inventive Principle:
Principle #18Mechanical vibration

2Measurement precision

If LiDAR or millimeter wave radar is used for short-range detection, then detection range is improved, but system cost and complexity increase significantly

Engineering Contradiction:
Improveshort-range detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces expensive LiDAR and millimeter wave radar systems with inexpensive piezoelectric elements. These low-cost sensors achieve the same short-range detection function without requiring multiple expensive sensors or complex sensor arrays, directly reducing system cost and complexity

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The patent makes the piezoelectric elements serve multiple functions: they both generate acoustic waves and detect acoustic wave signals. This dual functionality eliminates the need for separate transmission and reception sensors, simplifying the system architecture and reducing component count

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Area of stationary object

If highly directional proximity sensors are distributed throughout the robot to achieve full coverage, then detection coverage is improved, but system complexity and sensor management overhead increase

Engineering Contradiction:
Improvedetection coverage areaVSAvoidsensor distribution complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

The patent merges the functions of multiple directional sensors into a single omnidirectional acoustic wave detection system. By placing piezoelectric elements on the surface of the robot arm, the system achieves 360-degree detection coverage without requiring multiple distributed sensors, eliminating blind spots while simplifying the overall system architecture

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from one-dimensional linear array sensors to two-dimensional surface distribution of piezoelectric elements. This dimensional change enables omnidirectional detection capability, allowing the system to detect obstacles approaching from any direction without requiring multiple linear sensor arrays

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Provides accurate, omnidirectional, and cost-effective obstacle detection with no dead spots, requiring minimal modifications to the robot and effective at close ranges, reducing the risk of collisions.

Implementation Method 1

control a first one among piezoelectric elements disposed adjacent to a surface of an object, to generate an acoustic wave along the surface of the object

Methodology Applied
Scientific EffectPiezoelectric effect: Piezoelectric Effect

Implementation Method 2

receiving, via a second one among the piezoelectric elements, an acoustic wave signal corresponding to the generated acoustic wave

Methodology Applied
Scientific EffectPiezoelectric effect: Converse Piezoelectric Effect

Data Source

PatentUS12358170B2Method and apparatus for robot collision avoidance by full surface proximity detection
Publication Date: 2025.07.15 SAMSUNG ELECTRONICS CO LTD
  • US12358170B2 patent drawing
  • US12358170B2 patent drawing
  • US12358170B2 patent drawing

AI summary

An apparatus for collision avoidance by surface proximity detection includes a plurality of piezoelectric elements disposed adjacent to a surface of an object, a memory storing instructions, and at least one processor configured to execute the instructions to control a first one among the piezoelectric elements to generate an acoustic wave along the surface of the object, and receive, via a second one among the piezoelectric elements, an acoustic wave signal corresponding to the generated acoustic wave. The at least one processor is further configured to execute the instructions to filter the received acoustic wave signal, using a band-pass filter for reducing noise of the received acoustic wave signal, obtain a proximity signal for proximity detection, from the filtered acoustic wave signal, using a linear time-invariant filter, and detect whether an obstacle is proximate to the surface of the object by inputting the obtained proximity signal into a neural network.