The disclosure relates to a method for making sensor data more robust to adversarial perturbations, wherein sensor data are obtained from at least two sensors, wherein the sensor data obtained from the at least two sensors are replaced in each case piecewise by means of quilting, wherein the piecewise replacement is carried out in such a way that the respectively replaced sensor data from different sensors are plausible relative to one another, and wherein the sensor data replaced piecewise are output.

Provided are methods for detecting objects within a vehicle. The methods can include emitting at least one auditory signal within the vehicle during at least one first time interval; measuring a second auditory signal emitted by an object within the vehicle during the second time interval subsequent to the at least one first time interval, where the emission of the second auditory signal is caused by the emission of the least one first auditory signal; determining a location of the object within the vehicle based on the measurement of the second auditory signal; and generating an alert to a user indicating the location of that object. Systems and computer program products are also provided.

An autonomous vehicle includes an array of sensors, a processor, and a switch. The array of sensors generate sensor data related to one or more objects in an external environment of the autonomous vehicle and the processor determines an environmental context. The switch transfers the sensor data from the array of sensors to the processor, where the switch is configured to: (a) receive first sensor data from a first sensor group of the array of sensors; (b) receive second sensor data from a second sensor group of the array of sensors; (c) determine an order of transmission of the first sensor data over the second sensor data in response to the environmental context; and (d) transmit the first sensor data to the processor prior to transmitting the second sensor data based on the order of transmission.

In one implementation, a method includes: obtaining a first depth estimation characterizing a distance between the device and a surface in a real-world environment, wherein the first depth estimation is derived from image data including a representation of the surface; receiving, using the audio transceiver, an acoustic reflection of an acoustic wave, wherein the acoustic wave is transmitted in a known direction relative to the device; and determining a second depth estimation based on the acoustic reflection, wherein the second depth estimation characterizes the distance between the device and the surface in the real-world environment; and determining a confirmed depth estimation characterizing the distance between the device and the surface based on resolving any mismatch between the first depth estimation and the second depth estimation.

An autonomous guided vehicle includes a frame, a drive section, a payload handler, a sensor system, and a supplemental sensor system. The sensor system has electro-magnetic sensors, each responsive to interaction or interface of a sensor emitted or generated electro-magnetic beam or field with a physical characteristic, the electro-magnetic beam or field being disturbed by interaction or interface with the physical characteristic, and which disturbance is detected by and effects sensing of the physical characteristic. The sensor system generates sensor data embodying at least one of a vehicle navigation pose or location information and payload pose or location information. The supplemental sensor system supplements the sensor system, and is, at least in part, a vision system with cameras disposed to capture image data informing the at least one of a vehicle navigation pose or location and payload pose or location supplement to the information of the sensor system.

A processing load in a case where a plurality of different sensors is used can be reduced. An information processing apparatus according to an embodiment includes: a recognition processing unit (15, 40b) configured to perform recognition processing for recognizing a target object by adding, to an output of a first sensor (23), region information that is generated according to object likelihood detected in a process of object recognition processing based on an output of a second sensor (21) different from the first sensor.

Sensor data is received from an array of sensors configured to capture one or more objects in an external environment of an autonomous vehicle. A first sensor group is selected from the array of sensors based on proximity data or environmental contexts. First sensor data from the first sensor group is prioritized for transmission based on the proximity data or environmental contexts.

A system and method are provided for increasing the resolvability of an echo sounding system by acquiring multiple survey lines under one or more different conditions to produce overlapping swaths of seafloor data. The difference conditions may include one or more of acquiring the survey lines along adjacent paths that are offset by less than a swath width, acquiring survey lines at different headings, and acquiring survey lines at different speeds.

Sonar devices for detecting underwater objects are provided whereby a set of angled ultrasound transducers are employed to sense ultrasound signals from a plurality of different spatial regions. The angled ultrasound transducers may include a first pair of side-viewing ultrasound transducers and a second pair of ultrasound transducers configured for interrogating forward and reverse directions. The ultrasound signals from the set of angled ultrasound transducers may be processed to identify the presence of underwater objects in each spatial region, and the resulting identified underwater objects may be displayed, on a per-region basis, on a user interface. The ultrasound signals may additionally or alternatively be processed to generate a topographical model of the bed surface, and to generate a topographical surface image based on the three-dimensional topographical model. The topographical surface image may be displayed as a fly-over animation.

An acoustic-based Direction of Arrival (DoA) system uses acoustic information to determine the direction of incoming sound, such as a person talking. The direction of the sound is then used to focus a laser-based time of flight (ToF) system to narrow the area of laser illumination, improving the signal to noise ratio because laser illumination is focused on the direction of the sound. The DoA system also provides elevation information pertaining to the source of the sound, to further narrow the required field of view of the laser ToF system.