COLLISION DETECTION ON A MOBILE DEVICE

• Main Authors: LIU, RICHARD, G, VALANGET, PATRICE, O, CHOI HYUNGRYUL, LIAO YI WEN, GURISCH, EBERHARD, ALANAK ARMIN, RAGHURAM KARTHIK JAYARAMAN, MAJJIGI VINAY R, VENKATESWARAN, SIVAKUMAR, CHOW STEVE KUNG PAN, ZADEH PHILIP D. H, BRYAN PETER D, SUN TONG, HUSBAND, ANTONIUS, J., M, CLARKSON, RICHARD, L, PHAM HUNG A, AVILA NEDE, DAVID, O, AGARWAL MUKUL, AZIZ OFER, BAMR THOMAS, POPOVICH ANATOLY, RENARD YANN JEROME JULIEN, JACKSON, STEPHEN, PHILIP
• Format: Patent
• Language: Chinese; English
• Published: 08.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PERFORMING OPERATIONS; PHYSICS; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT; TRANSPORTING; VEHICLES IN GENERAL

The invention relates to collision detection on a mobile device. Embodiments for collision detection on one or more mobile devices (e.g., smartwatch and/or smartphone) are disclosed. In some embodiments, a method includes detecting, by at least one processor, a collision event on a collision device; extracting, by the at least one processor, a multi-modal feature from sensor data generated by a plurality of sensing modalities of the collision device; calculating, by the at least one processor, a plurality of collision decisions based on a plurality of machine learning models applied to the multi-modal feature; and determining, by the at least one processor, that a severe vehicle collision involving the collision device has occurred based on the plurality of collision decisions and a severity model. 本公开涉及移动设备上的碰撞检测。本发明公开了用于一个或多个移动设备(例如，智能手表和/或智能电话)上的碰撞检测的实施方案。在一些实施方案中，一种方法包括：通过至少一个处理器来检测碰撞设备上的碰撞事件；通过该至少一个处理器从由该碰撞设备的多个感测模态生成的传感器数据中提取多模态特征；通过该至少一个处理器基于应用于该多模态特征的多个机器学习模型来计算多个碰撞决定；以及通过该至少一个处理器基于该多个碰撞决定和严重性模型来确定已经发