http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Markus Lienkamp (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
Aditya Pathak,Matthias Binder,Fengqi Chang,Aybike Ongel,Markus Lienkamp 한국자동차공학회 2020 International journal of automotive technology Vol.21 No.1
In tropical countries, the power demand from the air conditioning system of an electric vehicle can be up to 40 percent of the total power demand of the traction battery. It is therefore essential to investigate methods that improve the efficiency to reduce the capital and operational costs of the vehicle. In public transportation, the frequent opening and closing of doors at bus stops results in a large influx of warm, humid ambient air into the cabin that increases energy consumption. The use of an air curtain is a potential solution that can minimise the infiltration of ambient air into the vehicle. The feasibility of implementation of an air curtain is however dependent on various factors such as the frequency of consecutive bus stops, duration of dwell time at bus stops, efficiency of the air conditioning system and the power consumed by the air curtain device. This paper investigates and compares the reduction of the air conditioning power consumption and the associated battery and energy costs with the use of air curtain in a 6 m mini-bus driving on selected bus routes in Singapore. The use of air curtain in an urban mini-bus is found to be economically feasible as the air conditioning power consumption for the studied routes reduced in the range of 20 ~ 28 %. Subsequently, energy and battery lifecycle costs reduced by 6 ~ 10 % based on the route, the frequency and duration of door openings.
-
Continuous Control of Autonomous Vehicles using Plan-assisted Deep Reinforcement Learning
Tanay Dwivedi,Tobias Betz,Florian Sauerbeck,PV Manivannan,Markus Lienkamp 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
End-to-end deep reinforcement learning (DRL) is emerging as a promising paradigm for autonomous driving. Although DRL provides an elegant framework to accomplish final goals without extensive manual engineering, capturing plans and behavior using deep neural networks is still an unsolved issue. End-to-end architectures, as a result, are currently limited to simple driving scenarios, often performing sub-optimally when rare, unique conditions are encountered. We propose a novel plan-assisted deep reinforcement learning framework that, along with the typical state-space, leverages a “trajectory-space” to learn optimal control. While the trajectory-space, generated by an external planner, intrinsically captures the agent’s high-level plans, world models are used to understand the dynamics of the environment for learning behavior in latent space. An actor-critic network, trained in imagination, uses these latent features to predict policy and state-value function. Based primarily on DreamerV2 and Racing Dreamer, the proposed model is first trained in a simulator and eventually tested on the F1TENTH race car. We evaluate our model for best lap times against parametertuned and learning-based controllers on unseen race tracks and demonstrate that it generalizes to complex scenarios where other approaches perform sub-optimally. Furthermore, we show the model’s enhanced stability as a trajectory tracker and establish the improvement in interpretability achieved by the proposed framework.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
