Smr Patents Sarl

Sony Group Corporation

Sony Semiconductor Solutions Corporation

Sony Corporation

Henrik Schäfer

Andreas Herrmann

Piergiorgio Sartor

Yalcin Incesu

Andrew Brian Little

Alexander Slama

Florian Becker

Peter Dürr

Bi Wang

Krishna Reddy Konda

Vincent Wilson

Pietro Zanuttigh

Ganeshan Narayanan

Kirk Scheper

Gianluca Agresti

Nikhil Satyakumar

Enrico Buratto

Harish S Bharadwaj

The present disclosure proposes a concept of training a machine learning network for use with a ToF camera. Based on a predefined synthetic scene, it is simulated a ground truth time resolved illumination return signal for a light pulse emitted from the ToF camera to the synthetic scene and scattered back from the synthetic scene to the ToF camera. The synthetic scene comprises a plurality of scene points with known distances between each of the scene points and the ToF camera. Based on the ground truth time resolved illumination return signal and a simulation model of the ToF camera, it is then simulated an output signal of at least one ToF pixel capturing the synthetic scene. Based on the simulated output signal of the ToF pixel and the ground truth time resolved illumination return signal, weights of the machine learning network are adjusted to cause the machine learning network to map the simulated output signal of the ToF pixel to an output time resolved illumination return signal approximating the ground truth time resolved illumination return signal.

Apparatuses and methods for training a machine learning network for use with a time-of-flight camera

The present disclosure relates to a collision avoidance concept comprising emitting a modulated light beacon from an object, wherein a luminance of the light beacon is modulated based on a useful signal carrying information on a position of the object, detecting, by an event-based vision sensor of a vehicle, the modulated light beacon of the object and outputting an event signal in response to a detected change in luminance of the modulated light beacon, and estimating a distance between the object and the vehicle based on the event signal.

Apparatuses and methods for collision avoidance

A method for autonomous in-flight transfer of a load from a first Aerial Vehicle, AV, to a second AV is provided. Each of the first AV and the second AV includes a frame with a vertical opening for receiving the load. A plurality of rotors are attached to the frame. The method comprising autonomously performing the following in-flight: fastening means of the first AV hold the load in the vertical opening of the first AV such that a bottom end of the load is accessible by the second AV; the second AV approaches the first AV from below in order to couple a fastening means of the second AV to the bottom end of the load; the fastening means of the first AV releases the load after the fastening means of the second AV couples to the bottom end of the load; and the fastening means of the second AV lower the load with respect to the frame of the second AV in order to move the load into a flight position.

Method for autonomous in-flight transfer of a load from a first aerial vehicle to a second aerial vehicle, system comprising a first aerial vehicle and a second aerial vehicle, and aerial vehicles

The present disclosure generally pertains to time-of-flight simulation data training circuitry, configured to:

Time-of-flight simulation data training circuitry, time-of-flight simulation data training method, time-of-flight simulation data output method, time-of-flight simulation data output circuitry

A method for transporting a rescue device from an aerial vehicle to a person to be rescued includes launching an unmanned aerial vehicle from the aerial vehicle having an end portion releasable attached to the unmanned aerial vehicle via a first connection and a second connection. The method further includes enabling the person to be rescued to reach the end portion of the rescue device. and determining whether the end portion of the rescue device is released from the first connection. If the rescue device is released determining at the unmanned aerial vehicle whether the person to be rescued is safely attached to the rescue device. If so, the method comprises either releasing the rescue device from the second connection, or deactivating the unmanned aerial vehicle such that the unmanned aerial vehicle remains attached to the rescue device via the second connection.

Method for transporting a rescue device from an aerial vehicle to a person to be rescued, rescue system for rescuing a person to be rescued, and unmanned aerial vehicle for transporting a rescue device from an aerial vehicle to a person to be rescued

A wiper device for a small and curved surface such as a spherical surface of an optical element includes at least one elongate wiper element with two ends, two drive units to which the ends of the wiper element are attached so that the wiper element can be moved on the surface of the optical element using the two drive units, and at least one contacting means for bringing the wiper element into contact with a surface of the optical element, the contacting means shapes the wiper element around at least that part of the surface which is exposed to the environment due to an opening provided by the housing and is to be cleaned.

Wiper device for spherical surfaces

A method for identifying a signaling state of at least one signaling device including a traffic light includes obtaining at least one image which includes an image of the at least one signaling device, extracting a region of the at least one image which includes the image of the at least one signaling device, detecting the at least one signaling device within the extracted region of the at least one image, and detecting a signaling state of the signaling device after detecting the at least one signaling device within the extracted region.

Method and device for identifying the signaling state of at least one signaling device

A method for identifying a signaling state of at least one signaling device from a plurality of signaling devices includes obtaining at least one image which comprises each of the plurality of signaling devices, representing at least one first group of the plurality of signaling devices detected by the image using a display device, receiving a user input regarding the display device or regarding a representation provided by the display device, evaluating the user input and selecting a second group from the first group of the plurality of signaling devices, and detecting a signaling state of the signaling devices of the second group and outputting a signal as a function of at least one detected signaling state of a signaling device of the second group in response to a change in the signaling state. A device for carrying out such a method is also described.

A wiping device for wiping an optical element clean of water or of particles includes a housing and a wiping element able to undergo a movement with respect to the housing, where the wiping device is configured to move in such a manner that such movement is caused by coupling a first unit in or on the wiping element with a second unit in the housing via a time-variable electromagnetic field. The wiping device may be used for wiping the surface of a lens or of a window, which lens or window is transmissive to visible light, ultraviolet radiation, and/or infrared radiation, and is preferably placed in front or as part of a camera. In addition, a rear view device or driver assistant device for use in or on a vehicle including such a wiping device, and a method for wiping an optical element are provided.

Growing community of inventors

Stuttgart, Germany

Henrik Schäfer