18145557. DRIVING DECISION-MAKING METHOD AND APPARATUS AND CHIP simplified abstract (Huawei Technologies Co., Ltd.)
Contents
DRIVING DECISION-MAKING METHOD AND APPARATUS AND CHIP
Organization Name
Inventor(s)
Yuzheng Zhuang of Shenzhen (CN)
DRIVING DECISION-MAKING METHOD AND APPARATUS AND CHIP - A simplified explanation of the abstract
This abstract first appeared for US patent application 18145557 titled 'DRIVING DECISION-MAKING METHOD AND APPARATUS AND CHIP
Simplified Explanation
The present disclosure is about driving decision-making methods, apparatuses, and chips. It describes a method that involves building a Monte Carlo tree based on the current driving environment state. The tree consists of a root node and several non-root nodes, each representing a different driving environment state. The driving environment states represented by the non-root nodes are predicted using a stochastic model of driving environments.
Based on the access count or value function of each node in the Monte Carlo tree, a node sequence is determined, starting from the root node and ending at a leaf node. This node sequence is used to determine a driving action sequence, where each node in the sequence corresponds to a specific driving action.
- The method involves building a Monte Carlo tree based on the current driving environment state.
- The tree includes a root node and several non-root nodes representing different driving environment states.
- The driving environment states represented by the non-root nodes are predicted using a stochastic model.
- The access count or value function of each node is used to determine a node sequence.
- The node sequence is used to determine a driving action sequence.
Potential applications of this technology:
- Autonomous driving systems: This method can be used in autonomous vehicles to make driving decisions based on the current environment state.
- Advanced driver assistance systems (ADAS): The method can be applied in ADAS to assist human drivers in making informed driving decisions.
- Traffic management systems: The technology can be utilized in traffic management systems to optimize traffic flow and reduce congestion.
Problems solved by this technology:
- Uncertainty in driving environments: The stochastic model used in this method helps predict driving environment states, addressing the uncertainty in real-world driving conditions.
- Decision-making in complex driving scenarios: The Monte Carlo tree approach allows for efficient decision-making in complex and dynamic driving situations.
Benefits of this technology:
- Improved safety: By considering various driving environment states and predicting potential outcomes, this method can help enhance driving safety.
- Enhanced efficiency: The use of Monte Carlo tree and stochastic modeling enables efficient decision-making, leading to optimized driving actions.
- Adaptability: The method can adapt to different driving scenarios and environments, making it suitable for various real-world applications.
Original Abstract Submitted
The present disclosure relates to driving decision-making methods, apparatuses, and chips. One example method includes building a Monte Carlo tree based on a current driving environment state, where the Monte Carlo tree includes a root node and N-1 non-root nodes, each node represents one driving environment state, and a driving environment state represented by any non-root node is predicted by a stochastic model of driving environments. Based on at least one of an access count or a value function of each node in the Monte Carlo tree, a node sequence that starts from the root node and ends at a leaf node is determined, and a driving action sequence is determined based on a driving action corresponding to each node in the node sequence.
