On-board Microprocessor Research Articles

Development of Real-Time Unmanned Aerial Vehicle Urban Object Detection System with Federated Learning

In this paper, an urban object detection system via unmanned aerial vehicles (UAVs) is developed to collect real-time traffic information, which can be further utilized in many applications such as traffic monitoring and urban traffic management. The system includes an object detection algorithm, deep learning model training, and deployment on a real UAV. For the object detection algorithm, the Mobilenet-SSD model is applied owing to its lightweight and efficiency, which make it suitable for real-time applications on an onboard microprocessor. For model training, federated learning (FL) is used to protect privacy and increase efficiency with parallel computing. Last, the FL-trained object detection model is deployed on a real UAV for real-time performance testing. The experimental results show that the object detection algorithm can reach a speed of 18 frames per second with good detection performance, which shows the real-time computation ability of a resource-limited edge device and also validates the effectiveness of the developed system.

ОЦЕНКА ЭНЕРГЕТИЧЕСКОЙ ЭФФЕКТИВНОСТИ ЛОКОМОТИВОВВ ЭКСПЛУАТАЦИИ

The article discusses the methodology for assessing the energy efficiency of locomotives under operating conditions according to data recorded by on-board microprocessor control systems of modern locomotives. It is based on the energy approach, which allows to estimate the losses in each element of energy conversion on the locomotive. The coefficient of efficiency of equipment operation and the energy resource overrun coefficient are proposed, which make it possible to assess the energy efficiency of the operation of traction equipment and the locomotive as a whole under operating conditions, as well as the resulting cost overrun of energy resources due to the predominance of operating modes other than nominal. The energy efficiency of the traction equipment of diesel locomotives 2TE25KM and TEP70BS was assessed.

Mathematical Methods for Validation of Data on Reliability, Operation and Maintenance of Locomotives

The objective of the article is to describe the method proposed by the authors and intended for validity check of initial data for managing reliability of locomotives and the entire locomotive facilities. It is shown that probabilistic-statistical methods which constitute the basis of Edward Deming’s theory of enterprise variability allowing to control the quality of enterprises’ products, including their reliability.The averaged statistical data used in practices of railway transport and its locomotive economy are not homogeneous, representing what is called in popular publications «average temperature of hospital patients». The homogeneity of data is determined by their unimodality, i.e., the presence of a single process in the sample. Unsuccessful sampling leads to its bimodality and even multimodality.The research method proposed in the article is check for unimodality of the initial data based on the consequence of the law of large numbers, according to which, with an increase in the number of data, homogeneous samples tend to one of the laws of distribution of random variable: to normal, exponential, lognormal or other known law. Therefore, and since any unimodal sample must meet a goodness-of-fit test, the article proposes to apply Pearson’s chisquare test (χ2). The unimodality of the data is suggested to be estimated through the probability of compliance with the chosen law of distribution of a random variable considering the probability of more than 0,3 (30 %) to be sufficient.Using the example of locomotive operation data and on-board microprocessor systems data, data are shown that cannot really be unimodal, as well as the data that require changing the sampling rules to achieve unimodality. For example, when considering the average daily runs of locomotives by series at specific home depots with participation in one type of traffi (main traffi export, or shunting operations), their unimodality is achieved. An attempt to enlarge the data (to consider several series, several polygons, etc.) results in loss of unimodality.The article considers the unimodality of data of MSU-TP on-board microprocessor control systems for diesel locomotives of 2TE116U series. The expected operating time for the positions of the driver’s controller turned out to be multimodal data. Surprisingly, the current of the traction motors turned out to be unimodal, regardless of the driving position of the driver’s controller.

A lower limb rehabilitation platform with mirror therapy, electrical stimulation and virtual reality for people with limited dorsiflexion movement

This paper presents a low-cost portable system for applying a rehabilitation therapy, based on virtual reality, functional electrical stimulation and a training device. This open-hardware system, intended to support a home-made therapy process in people with reduced dorsiflexion ability, contains three main building blocks: an electromechanical platform, an immersive virtual reality interface and the firmware. The electromechanical training platform is the core of the system, which acts as a gateway interface of sensors-actuators for a closed loop system, through an immersive virtual reality application, the patient closes the loop by acting as the controller by means of a “virtual dummy” preforming in mirror configuration.The platform measures and process the dorsiflexion angle described by both ankles, real-time transmitting the information to the mobile phone virtual application to be presented as a mirror. The onboard microprocessor drives the operation of the electric stimulation interface, which is sent through two channels to both, healthy and affected lower limbs. The platform communicates continuously through a USB bidirectional interface with a personal computer, in which the physician enters the rehabilitation protocol and follows the patient performance. A first case study by using this device has been reported in [1].

An improved central difference Kalman filter for satellite attitude estimation with state mutation

AbstractThere are three problems in applying central difference Kalman filter (CDKF) to attitude estimation of low‐cost satellite: (1) the negative definiteness and asymmetry of the covariance matrix caused by limited computing power and storage space of the onboard microprocessor may result in calculation divergence, (2) the system model uncertainty including model mismatch and state mutation caused by environmental disturbances from inside and outside the satellite will lead to filter divergence, (3) the addition operation on quaternions violates the normalization constraint, while enforced unitization will introduce approximation errors. To solve the above problems, this article proposes the multiplicative quaternion square root strong tracking CDKF (MQSRSTCDKF), in which three improvements to basic CDKF are made: (1) square roots of covariance matrices are adopted for information propagation in place of covariance matrices themselves, which always guarantees the symmetry and positive definiteness of covariance matrices, (2) multiple fading factors are employed to adjust square root of the covariance matrix of predicted state variables, and then adjust the gain matrix to make the filter attach more weight to sensor measurements than to corrupt state predictions caused by model uncertainties, (3) multiplication operation on quaternions is conducted instead of the addition one, which makes the normalization constraint on quaternions naturally satisfied without enforced unitization. Numerical simulation based on raw telemetry data from the on‐orbit CubeSat NJUST‐1 shows that MQSRSTCDKF has higher attitude estimation accuracy, faster convergence speed, and stronger robustness to filter divergence and calculation divergence than basic CDKF.

Automation of vibration modes of soil compaction machines

The relevance of high-quality compaction of soil foundations during the construction of embankments and foundations during the construction of engineering structures is given. An effective vibrodynamic method of compaction of gravel and sand materials for foundations of building structures for various purposes is substantiated and proposed. The method of continuous monitoring of the degree of compaction of the soil by measuring the magnitudes of the amplitudes and frequencies of harmonic oscillations of the compacted surface is determined. A schematic diagram of the automatic control system CAP of vibration modes of shock-absorbing soil compacting machines with a crank-oscillating exciter is proposed. The principle of regulating the operating modes of a vibrating machine using an automatic control pulse distributor is stated. A structural block diagram of the CAP elements is constructed and an analysis of the dynamic properties that determine the optimal control time is carried out. The main elements of the CAP are determined and their work in the control program is shown: the frequency of impact of the working mechanism on the soil surface being compacted, depending on the degree of compaction. Key words: soil compaction degree, operating mechanism, amplitude and frequency of harmonic oscillations of the surface of the soil being compacted, vibro-shock machines with a crank-connecting rod exciter, automatic control system, control pulse distributor, process parameters sensors, on-board microprocessor controller.

ROS Based Autonomous Robot with Open CV

In this project, we have designed and developed an autonomous robot that is powered by Robot Operating System (ROS). The capabilities of the robot include autonomous navigation, image tracking and mapping. OpenCV has been implemented in the on-board microprocessor to process the images that are captured by the general purpose webcams on the robot. A microcontroller has also been used to control the motors. The ultimate aim of this project is to develop a mobile robot capable of making its own decisions based on the images received.

A Fiducial Scaffold for ECG Compression in Low-Powered Devices.

Large volumes of physiological data can now be routinely collected using wearable devices, though a key challenge that remains is the conversion of raw data into clinically relevant and actionable information. While power constraints prevent continuous wireless streaming of large amounts of raw data for offline processing, on-board microprocessors have become sufficiently powerful for data reduction to be performed in real time on the wearable device itself, so that only aggregate, clinically interpretable measures need to be transmitted wirelessly. Here, we use the curve-length transform to extract key beat-by-beat information from the raw ECG waveform, and to identify clinically relevant timing and amplitude information. Each beat is parameterized by 12 morphological features that serve as fiducial markers, sufficient to directly reconstruct a scaffold representation of the ECG waveform. At a nominal heart rate of 70 beats/min and a sampling rate of 250 Hz, typical for wearable monitors, this represents approximately an 18-fold compression. Using difference encoding, the compression ratio improves to 21. Our algorithm computes a running exponentially-weighted average of each identified morphological feature. When any feature deviates significantly from its running average, the algorithm retains the raw waveform for five beats preceding and following the anomaly, enabling future review of the raw data. The algorithm automatically located 93.8% of the 3,615 expert-annotated QRS onsets and offsets in the PhysioNet QT-Database to within 20 ms. Similarly, it located 83.5% of all 3,194 P-wave onset and offset annotations to within 32 ms, and 89.0% of all 3,542 T-wave offset annotations within 72 ms.

Using ANT Communications for Node Synchronization and Timing in a Wireless Ultrasonic Ranging System

Indoor localization and tracking of persons and assets for gaming, augmented reality, medical monitoring, training, security, and inventory is an emerging technology. Localization can be computed from multiple distance measurements between reference beacons and sensors. Low cost, small, light, tiny-battery, or even batteryless operated sensors are required. Ranging can be carried out by measuring the time of flight of an ultrasonic chirp traveling from an emitting beacon to receiving sensors. That requires a tight synchronization between the beacon and the sensors. In this article, we present a ranging system based on miniature commercial modules featuring ANT wireless personal area network communication plus onboard microprocessor. A protocol is developed for microseconds synchronization and accurate onboard ranging computations are carried out through ultrasonic signal cross correlation. The sensor privately computes its own range. The ranging system is composed of a synchronizing unit, a beacon emitting ultrasonic chirps, and a battery-operated distance sensor. The sensor shows low average power consumption (less than 22 mW) and a ranging accuracy of about 1.8 mm for distances up to 2.5 m, under stable environmental conditions.

An Routing Algorithm in Wireless Sensor Networks Using Cluseter Tree Topology

Introduction At present, there has been a mounting requirement for connectivity between the distributed devices employed for remote instantaneous monitoring and control. This requirement and the development in electronics and wireless communications have encouraged the growth of Wireless Sensor Network (WSN) technology as explained in Alwan& Agarwal (2009). A WSN is an integration of embedded system technology together with sensor technology, distributed computing and wireless communication technology. They allow superior grain inspection of the ambient surroundings at an inexpensive cost much lesser than currently possible. In case of hostile surroundings where human involvement may perhaps be too hazardous, sensor networks might offer a robust service. Sensor networks are intended to send out data from an array of sensor nodes to a data storehouse on a server. The developments in the integration of Micro-Electro-Mechanical System (MEMS), moreover Microprocessor and Wireless Communication technology have facilitated the use of large-scale WSNs. WSN has the adequate power to design several new applications for the purpose of managing emergency, military, and tragedy relief processes that necessitates real time information for effective coordination and planning. Sensor nodes have the potential of sensing, data processing, and transmission, which facilitate instantaneous monitoring of the phenomenon of attention, and control by actuators inside a large-scale area by collaborating with each other as discussed in Megerian & Potkonjak (2003) WSNs possibly will include numerous categories of sensors like thermal, magnetic, seismic, infrared, visual and acoustic radar, capability to supervise an extensive variety of ambient circumstances. Despite the fact that every individual sensor possibly will have severe resource restriction in terms of memory, communication, energy and computation capabilities; huge number of them might together observe the physical world, distribute information upon critical environmental occurrences, and process the information on the fly as discussed in Akyildiz et al (2002). The major characteristics of sensor networks comprise low energy consumption, low cost, cooperative effort and self-organizing operation as mentioned in Lambrou & Panayiotou (2009). These characteristics make it feasible to organize sensor nodes in harsh and unreachable surroundings, at the same time achieving long lifetime operation with the help of batteries and solar panels as the energy supply. The characteristics described above allow an extensive range of potential applications for WSNs, like industrial control and monitoring, precision agriculture, home automation, health and environmental observation. The overview of the WSN architecture is portrayed in the figure 1.1. Figure 1. An Overview of a WSN Figure 1.1 The Components of a Sensor Node A sensor node normally includes a processing unit, a sensing unit, a radio frequency transceiver unit and a power supply unit. Figure 1.2 illustrates the component chart of a sensor node. In case of the processing unit, which typically incorporates an on-board microprocessor and also memory, manages the function of the other units and executes simple data processing. In case of the sensing unit, the sensors are linked to the processing unit by means of analog-to-digital converters, which transform the analog signals produced by the sensors into digital signals that the microprocessor can understand. The radio frequency transceiver unit is the gateway that swaps over data with other sensor nodes by means of a wireless communication channel. These components might possess different features in terms of input voltage and current utilization, and the power supply unit offers the suitable voltage and current intensities. In case of the power supply unit, energy storage constituents (e.g., a battery) are adjusted by the appropriate electrical circuitry and energy harvesting constituents (e.g., a solar panel). In accordance with the particular application, other units can be too added to the sensor node, like a location finding system and a mobilize, as discussed in Chalhoub & Mission (2010) which maintain the request for precise geographical information and the mobility of a sensor node, correspondingly

Development of the method of efficient monitoring of the main activity of a train driver

A method of monitoring the state of a train driver with the use of his/her individual standard and the rules of the justified differential interference in the operating activity was developed. This gives an opportunity to increase the train motion safety up to qualitatively new level. Furthermore, the method makes it possible to effectively control the reliability of the “human factor”, a train driver, under real conditions. As a result of the studies, the algorithm of specifying the degree of a train driver’s behavior deviation from his/her normal state during the process of controlling the train was suggested.Its essence lies in specifying the “not a standard”state by defining four levels: critical, warning, preventive and informational. Each level requires different actions regarding the interference in the control process of a train. The directions of the justified corrective actions concerning the control of the locomotive were determined. The criteria of their estimation were obtained due to practical application of the system approach, the characteristic feature of which is the use of dependence of the dispersion on the functional state of the system, and Shewhart's Control Charts.The suggested method uses contemporary transport technologies, digital onboard instruments and microprocessor devices; it does not require additional equipment in the cabin (bracelets, buttons, handles, etc.). Technical application of the method can be integrated practically into any form of the traction rolling stock. In this case, a new form of vigilance control does not distract a train driver from the main activity and does not require any significant capital investments.

COMPARISON OF FEASIBILITY OF RISK MONITORING IN BUILDINGS IN TWO WIRELESS SENSOR NETWORK: MICA MOTE AND MEMS

In this paper feasibility of risk monitoring of buildings in two wireless sensor network is presented, firstly by using MICA Mote and then by MEMS. Also, it will be verified that the MEMS sensors are superior as it provides high quality sensor data and no data loss as compared to MICA Mote. In order to assess earthquakes the structures is monitored firstly by using a smart sensor based on the Berkeley Mote platform. The Mote has on-board microprocessor and ready-made wireless communication capabilities. In this paper, the performance of the Mote is investigated through shaking table tests employing a two-story steel structure. The feasibility of risk monitoring for buildings is also discussed. In building monitoring using MEMS, a low power wireless network employing capacitive MEMS which is custom-developed,3D accelerated sensor and a low power readout ASIC is used at the sensor nodes. After the the earthquake, the plastic hinge activation of structure is being measured using MEM sensor either periodically or on demand by the base station. During an earthquake the accelerometers are used to measure the seismic response of the structure. The seismic response is recorded by the accelerometer based on the local acceleration data and remote triggering from the base station. The base station is based on acceleration data from multiple sensors across the structure. In a 800 MHZ band, a low power architecture had been implemented over an 802.15.4 MAC.

Exo-Leg: An Active Single-Leg External Walking Assist Device

Lower extremity weakness is a serious problem afflicting people all over the world. Until recently, the mobility options for people with this condition have been confining and limit the individual’s functionality. Walking assist devices are presently in development to restore hands-free walking to people with lower extremity weakness. These devices provide the necessary support and power to enable the individual to restore normal ambulation. The proposed design of exoleg, a single leg external walking assist device, addresses the demographic of people with lower extremity weakness. The design includes replication of the gait cycle utilizing mechanical links and user control interface with emphasis on safety. The design couples the actuation of the knee and hip through the use of linkages connected to a single motor. The actuation of the hip is controlled by a 4 bars crank-rocker linkage system while the knee is actuated by corresponding linkages (designed in WORKING MODEL 2D, a commercial simulation software) that generates the knee kinematic profile. The angular profiles of the knee and hip actuations are compared with the actual knee and hip angular trajectories. The frame of the device incorporates a passive ankle stabilization system to compensate for the effects of foot drop. The system utilizes feedback from trigger points from pressure sensors on the foot and goniometers at the hip and knee joints to measure the angulations in gait to keep the device in synchronization with natural ambulation. An on-board microprocessor receives the feedback from the trigger points and sends the actuation signal to the motor. A conceptual design of electrostatic actuator motor is also proposed to keep the device light weight and compact.

A wireless recording system that utilizes Bluetooth technology to transmit neural activity in freely moving animals

A new wireless transceiver is described for recording individual neuron firing from behaving rats utilizing Bluetooth transmission technology and a processor onboard for discrimination of neuronal waveforms and associated time stamps. This universal brain activity transmitter (UBAT) is attached to rodents via a backpack and amplifier headstage and can transmit 16 channels of captured neuronal firing data via a Bluetooth transceiver chip over very large and unconstrained distances. The onboard microprocessor of the UBAT allows flexible online control over waveform isolation criteria via transceiver instruction and the two-way communication capacity allows for closed-loop applications between neural events and behavioral or physiological processes which can be modified by transceiver instructions. A detailed description of the multiplexer processing of channel data as well as examples of neuronal recordings in different behavioral testing contexts is provided to demonstrate the capacity for robust transmission within almost any laboratory environment. A major advantage of the UBAT is the long transmission range and lack of object-based line of sight interference afforded by Bluetooth technology, allowing flexible recording capabilities within multiple experimental paradigms without interruption. Continuous recordings over very large distance separations from the monitor station are demonstrated providing experimenters with recording advantages not previously available with other telemetry devices.

An evaluation on the multi-agent system based structural health monitoring for large scale structures

Different kinds of sensors have to be adopted to have a reliable monitoring of large scale engineering structures. Multi-agent system (MAS) based structural health monitoring (SHM) technology is researched to deal with the diverse, heterogeneous and distributed information. This paper introduces an evaluation on a multi-agent system based structural health monitoring to validate the efficiency of the multi-agent technology. Through the cooperation of different agents and different subsystems, the whole system can fuse three kinds of sensor information including strain gauge sensor, fiber optic sensor and piezoelectric sensor, can automatically choose sensing object, can self-organize the sensor network and discard useless sensor data, and can recognize three typical kinds of structure states which may indicate structural damages including impact load, joint failure, strain distribution change on every substructure and the edge area between two adjacent substructures. In the evaluation work besides adopting conventional monitoring instruments, the strain signal of the strain gauge is also demonstrated to be monitored by smart wireless sensor with on-board microprocessor developed in the lab. In this paper the evaluated experimental aluminium plate and the sensor distribution are firstly introduced. The corresponding agents are defined based of the designed multi-agent system frame presented by the authors. The monitoring strategies in the validation work including monitoring principle and monitoring equipments for three typical kinds of structure states are proposed. After the process of developing the impact load diagnostic agent as the basis work of the whole system is introduced in detail, the implementation of the whole multi-agent system based structural health monitoring for the plate is presented. This paper shows the efficiency of the multi-agent technology for the development of the SHM system on the large practical structures.

Human Activity Monitoring System Using MEMS Sensors and Machine Learning

Observation of daily human activity and status is important from the viewpoints of maintaining health and preventive medical care. In this study, we describe a system for monitoring human activities and conditions that uses microelectromechanical systems (MEMS) sensors. The system contains four MEMS sensors for environmental monitoring-3-axis acceleration, barometric pressure, temperature, and relative humidity -as well as the peripheral circuitry for each sensor. Measured human activity data are stored in a memory via an on-board microprocessor. We measured environmental data for a subject's daily life. To estimate the subject's activity and his condition from a huge volume of data, we applied a soft computing technique to machine learning for the automatic extraction of human-activity classification.

Revolutionary Advances in Medical Waste Management. The Sanitec® System

It is the purpose of this collective review to provide a detailed outline of a revolutionary medical waste disposal system that should be used in all medical centers in the world to prevent pollution of our planet from medical waste. The Sanitec medical waste disposal system consists of the following seven components: (1) an all-weather steel enclosure of the waste management system, allowing it to be used inside or outside of the hospital center; (2) an automatic mechanical lift-and-load system that protects the workers from devastating back injuries; (3) a sophisticated shredding system designed for medical waste; (4) a series of air filters including the High Efficiency Particulate Air (HEPA) filter; (5) microwave disinfection of the medical waste material; (6) a waste compactor or dumpster; and (7) an onboard microprocessor. It must be emphasized that this waste management system can be used either inside or outside the hospital. From start to finish, the Sanitec Microwave Disinfection system is designed to provide process and engineering controls that assure complete disinfection and destruction, while minimizing the operator's exposure to risk. There are numerous technologic benefits to the Sanitec systems, including environmental, operational, physical, and disinfection efficiency as well as waste residue disinfection. Wastes treated through the Sanitec system are thoroughly disinfected, unrecognizable, and reduced in volume by approximately 80% (saving valuable landfill space and reducing hauling requirements and costs). They are acceptable in any municipal solid waste program. Sanitec's Zero Pollution Advantage is augmented by a complete range of services, including installation, startup, testing, training, maintenance, and repair, over the life of this system. The Sanitec waste management system has essentially been designed to provide the best overall solution to the customer, when that customer actually looks at the total cost of dealing with the medical waste issue. The Sanitec system is the right choice for healthcare and medical waste professionals around the world.

Distributed computing strategy for structural health monitoring

Monitoring of complex structures to provide real-time safety and reliability information regarding the structure poses significant technical challenges. To detect damage in large civil infrastructure systems, densely distributed sensors are expected to be required. Use of traditional wired sensors is challenging for such applications because of the cost and difficulty in deploying and maintaining a large wiring plant. Using wireless sensor network is also difficult because large amounts of measured data need to be transferred to a central station. The bandwidth and power requirement to transfer these data may easily exceed the limit of the wireless sensor. Recently rapid advances in smart sensor technologies have made damage detection using a dense array of sensors feasible. The essential feature of a smart sensor is the on-board microprocessor, which allows smart sensors to make decisions, perform computation, save data locally, etc. By conducting a portion of the computation at the sensor level, only limited information needs to be transferred back to a central station. However, damage detection algorithms which can take advantage of the distributed computing environment offered by smart sensors are currently limited. In this paper, a new distributed computing strategy for structural health monitoring is proposed that is suitable for implementation on a network of densely distributed smart sensors. In this approach, a hierarchical strategy is proposed in which adjacent smart sensors are grouped together to form sensor communities. A flexibility-based damage detection method is employed to evaluate the condition of the local elements within these communities by utilizing only locally measured information. The damage detection results in these communities are then communicated with the surrounding communities and sent back to a central station. Numerical simulation demonstrates that the proposed approach works well for both single and multiple damage scenarios. Copyright © 2005 John Wiley & Sons, Ltd.

Distributed structural health monitoring system based on smart wireless sensor andmulti-agent technology

This paper presents a new parallel distributed structural health monitoring technologybased on the wireless sensor network and multi-agent system for large scale engineeringstructures. The basic idea of this new technology is that of adopting the smart wirelesssensor with on-board microprocessor to form the monitoring sensor network and themulti-agent technology to manage the whole health monitoring system. Using thistechnology, the health monitoring system becomes a distributing parallel system instead ofa serial system with all processing work done by the central computer. The functions, thereliability, the flexibility and the speed of the whole system will be greatly improved. Inaddition, with wireless communication links instead of wires, the system weight andcomplexity will be lowered. In this paper, the distributed smart wireless sensor network isdesigned first based on the Berkeley Mote Mica wireless sensor platform. Two kinds ofsensor have been adopted: piezoelectric sensors and electric resistance wires. Theyare connected to a Mica MPR board though a designed charge amplifier circuitor bridge circuit and MTS101 board. Seven kinds of agents are defined for thestructural health monitoring system. A distributed health monitoring architecturebased on the defined agents is proposed. Finally, a composite structural healthmonitoring system based on a Mica wireless platform and multi-agent technology isdeveloped to evaluate the efficacy of the new technology. The developed systemcan successfully monitor the concentrated load position or a loose bolt position.

Two brains, one car - actively controlled steering

Actively controlled steering (ACS) systems enable vehicle autonomy and facilitate the trend in active stabilization and control that has been developing steadily over the last decade. These systems can improve the overall driving experience. Employing an on-board microprocessor, ACS is both a necessary enabler for fully autonomous vehicular operations and a functional element that can improve a car's operational envelope independent of autonomous operation. In the paper, examples of ACS are given, and BMW's active steering system and stability controllers based on ACS systems are discussed.