Sound propagation and perception for autonomous agents in dynamic environments

• US 9,942,683 B2
• Filed: 07/16/2014
• Issued: 04/10/2018
• Est. Priority Date: 07/16/2013
• Status: Active Grant

• Current Assignee: Trustees Of The University Of Pennsylvania (University of Pennsylvania)
• Original Assignee: Trustees Of The University Of Pennsylvania (University of Pennsylvania)
• Inventors: Badler, Norman I., Huang, Pengfei, Kapadia, Mubbasir
• Primary Examiner(s): Sniezek, Andrew L
• Application Number:
  US14/904,819
• Publication Number:
  US 20170171684A1
• Time in Patent Office: 1,364 Days
• CPC Class Codes: G10L 25/18 the extracted parameters being spectral information of each sub-band
• CPC Class Codes: H04S 2400/11 Positioning of individual sound objects, e.g. moving airplane, within a sound field H04S2420/13 takes precedence
• CPC Class Codes: H04S 2420/07 Synergistic effects of band splitting and sub-band processing
• CPC Class Codes: H04S 7/30 Control circuits for electronic adaptation of the sound field

Abstract

Methods and systems for sound propagation and perception for autonomous agents in dynamic environments are described. Adaptive discretization of continuous sound signals allows one to obtain a minimal, yet sufficient sound packet representation (SPR) for human-like perception, and a hierarchical clustering scheme to facilitate approximate perception. Planar sound propagation of discretized sound signals exhibit acoustic properties such as attenuation, reflection, refraction, and diffraction, as well as multiple convoluted sound signals. Agent-based sound perceptions using hierarchical clustering analysis that accommodates natural sound degradation due to audio distortion facilitate approximate human-like perception.

Claims

1. A device comprising:

a processor; and

a memory coupled with the processor, the memory having stored thereon executable instructions that when executed by the processor cause the processor to effectuate operations comprising;

providing information to an agent that arrives at a ground location of the agent, wherein;

the information comprises an impulse response of a plurality of packets at different frequency bands, and

the agent is virtual;

applying dynamic time warping to the plurality of packets; and

determining similarity values based on comparison of the applied dynamic time warping of the plurality of packets with sounds in a hierarchical clustering analysis database.

2. The device of claim 1, wherein the information further comprises a spread factor that is computed for each of the plurality of packets which indicates a frequency and amplitude changes due to each of the plurality of the packets interacting with a virtual environment.

3. The device of claim 1, wherein the information further comprises a spread factor that is computed for each of the plurality of packets that interact with a virtual environment, wherein the interaction with the virtual environment comprises reflection.

4. The device of claim 1, wherein the agent approximately localizes a sound source based on the plurality of packets it receives.

5. The device of claim 1, wherein the agent uses an attention model to facilitate sound identification in the presence of convoluted sounds, background noise, or sound novelty.

6. The device of claim 1, wherein the agent has sound perception that can be used as inputs to agent behavior controls to affect actions, motions, or decisions of the agent.

7. The device of claim 1, wherein the information further comprises a spread factor that is computed for each of the plurality of packets wherein the based on the each of the plurality of packets interaction with a virtual environment, wherein the interaction with the virtual environment comprises absorption.

8. The device of claim 1, further operations comprising:

determining that the similarity values are above a similarity threshold; and

after determining that the similarity values are above the similarity threshold, providing an approximate perception based on a lowest common ancestor in the hierarchical clustering analysis database.

9. The device of claim 8, further operations comprising using the approximate perception as a control signal to trigger a behavior of the agent.

10. The device of claim 1, wherein the information further comprises a spread factor that is computed for each of the plurality of packets that interact with a virtual environment, wherein the interaction with the virtual environment comprises diffusion.

11. The device of claim 1, wherein the information further comprises a spread factor that is computed for each of the plurality of packets that interact with a virtual environment, wherein the interaction with the virtual environment comprises amplitude attenuation.

12. A computer readable storage medium that is not a signal storing computer executable instructions that when executed by a computing device cause said computing device to effectuate operations comprising:

providing information to an agent that arrives at a ground location of the agent, wherein;

the information comprises an impulse response of a plurality of packets at different frequency bands, and

the agent is virtual;

applying dynamic time warping to the plurality of packets; and

determining similarity values based on comparison of the applied dynamic time warping of the plurality of packets with sounds in a hierarchical clustering analysis database.

13. The computer readable storage medium of claim 12, wherein the information further comprises a spread factor that is computed for each of the plurality of packets which indicates a frequency and amplitude changes due to each of the plurality of the packets interacting with a virtual environment.

14. The computer readable storage medium of claim 12, wherein the information further comprises a spread factor that is computed for each of the plurality of packets that interact with a virtual environment, wherein the interaction with the virtual environment comprises reflection or diffusion.

15. The computer readable storage medium of claim 12, wherein the agent approximately localizes a sound source based on the plurality of packets it receives.

16. The computer readable storage medium of claim 12, wherein the agent uses an attention model to facilitate sound identification in the presence of convoluted sounds, background noise, or sound novelty.

17. The computer readable storage medium of claim 12, wherein the agent has sound perception that can be used as inputs to agent behavior controls to affect actions, motions, or decisions of the agent.

18. The computer readable storage medium of claim 12, wherein the information further comprises a spread factor that is computed for each of the plurality of packets wherein the based on the each of the plurality of packets interaction with a virtual environment, wherein the interaction with the virtual environment comprises absorption or amplitude attenuation.

19. The computer readable storage medium of claim 12, further comprising:

determining that the similarity values are above a similarity threshold; and

after determining that the similarity values are above the similarity threshold, providing an approximate perception based on a lowest common ancestor in the hierarchical clustering analysis database.

20. The computer readable storage medium of claim 19, further comprising using the approximate perception as a control signal to trigger a behavior of the agent.