Search Results

Rotating clutches play an important role in automatic transmissions (AT), dual-clutch transmissions (DCT) and hybrid transmissions. It is very important to continually improve the transmission systems in the areas such as simplifying actuator designs, reducing cost and increasing controllability. A new concept of electrical motor driven actuation using a wedge mechanism, a wedge clutch, demonstrates potential benefits. This wedge clutch has the characteristics of good mechanical advantage, self-reinforcement, and faster and more precise controllability using electrical motor. In this paper, a new rotating wedge clutch is proposed. It presents a challenge since the motor actuator has to be stationary while the clutch piston is rotating. A new mechanism to connect the motor to the wedge piston, including dual-plane bearings and two mechanical ramp linkages, is studied. The design and verification of the physical structure of the actuator are discussed in detail in the paper.

Precise trajectory prediction of surrounding vehicles is critical for decision-making of autonomous vehicles, and learning-based approaches are well recognized for the robustness. However, state-of-the-art learning-based methods ignore (1) the feasibility of the vehicle’s multimodal state information for prediction and (2) the mutually exclusive relationship between the global traffic scene receptive fields and the local position resolution when modeling vehicles’ interactions, which may influence prediction accuracy. Therefore, we propose a “vehicle descriptor”-based long short-term memory (LSTM) model with the dilated convolutional social pooling (VD+DCS-LSTM) to cope with the above issues.