Local anti-pursuit method for unmanned surface vehicle based on aggregation of spatial-temporal characteristics

Abstract

The invention discloses a local anti-pursuit method for an unmanned surface vehicle based on aggregation of spatial-temporal characteristics. At the present stage, a local navigation algorithm of an unmanned surface vehicle is mainly used for carrying out local collision avoidance path planning on dynamic obstacles in static and uniform linear motion, and the unmanned surface vehicle may be pursued due to behaviors such as out-of-control operation or malicious blocking, so that the navigation safety of the unmanned surface vehicle is greatly threatened. The invention provides an anti-pursuit path planning method suitable for a complex water surface environment, and the method comprises the steps: simulating a multi-source shipborne sensor to generate a simulation signal, providing environment perception data, constructing a coding structure of aggregated spatial-temporal characteristics, and distinguishing dynamic and static obstacles in a scene, and constructing an end-to-end navigation path planning model by adopting a value distributed reinforcement learning algorithm. According to the invention, the motion characteristics of the obstacle in the environment can be identified, so that the decision-making ability and the navigation robustness of the unmanned ship in a complex environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent unmanned ships, and in particular to an end-to-end unmanned boat local navigation planning method that aggregates spatiotemporal features. Specifically, the present invention relates to a method that extracts environmental observation information using a spatiotemporal feature coding structure as input to a deep reinforcement learning algorithm, and guides the unmanned boat to autonomously allocate weight information to achieve local obstacle avoidance. Background Art

[0002] Unmanned surface boats have been the research focus in the field of smart ships and intelligent shipping in recent years. Improving the autonomous navigation capabilities of ships is inseparable from their own real-time path planning capabilities and high-reliability obstacle avoidance capabilities. In the past five years, a large number of emerging studies have emerged in the field of ship path planning. These works focus on designing different navigation scenarios to verify the path planning capabilities of decision-making algorithms. Global path planning, researchers obtain static environmental features through electronic charts and other information, and plan a route from the starting point to the end point. This type of algorithm only needs to adjust the trajectory when the ship deviates significantly from the preset path, and there is no need to update the planned path in real time. Local path planning, through the real-time acquisition of surrounding obstacle information to guide the speed and heading angle changes of the ship at the next moment, this algorithm needs to perceive environmental information in real time and make reasonable motion decisions.

[0003] This paper focuses on the field of local path planning, and explores the local anti-pursuit method of unmanned boats in complex eddy interference environments such as high-dynamic pursuers and high-density obstacles. It studies end-to-end robust ship motion decision-making technology to achieve real-time, high-reliability autonomous collision avoidance and navigation planning for unmanned boats in scenarios without prior information. Summary of the invention

[0004] Technical problem: The technical problem to be solved by the present invention is to provide a robust navigation planning method for surface unmanned boats that aggregates spatiotemporal characteristics in the direction of local path planning involved in the background technology, targeting high-dynamic pursuers, high-density obstacles and eddy-interfered water surface environments, to achieve real-time collision avoidance of ships with obstacles in various motion modes.

[0005] Technical solution: To solve the above technical problems, the present invention adopts a local anti-pursuit method for unmanned surface boats that aggregates spatiotemporal characteristics. The method comprises:

[0006] Step 1: Define the scope of the local navigation area, set the starting and ending coordinates of the surface unmanned boat in the area, and randomly generate eddy current signals in the area;

[0007] Step 2: Construct a navigation environment and randomly generate static obstacles of different sizes and dynamic obstacles of random positions in the blank area;

[0008] Step 3: Based on the type of sensors carried by the real ship, generate a simulated signal that provides information on speed, the ship's own position, and the relative distance of obstacles, and use this to construct an observation signal;

[0009] Step 4: Send the observation signal to the spatiotemporal feature aggregation module to aggregate the spatial features in a frame-by-frame stacking manner along the time dimension; and input the observation signal frame by frame into the continuous time neural network to aggregate the temporal features;

[0010] Step 5: Determine the distributed reinforcement learning algorithm as the backbone framework of the navigation planning network and define the action space and reward function;

[0011] Step 6: Use the experience pool to collect experience data during the training process, optimize the network weight parameters with small batches of experience data, and use the experience replay strategy to train the deep reinforcement learning model until convergence;

[0012] Step 7: Build an experimental verification scenario, load the converged model parameters, and verify the ship's anti-pursuit and collision avoidance capabilities in the local environment and its generalization capabilities to cope with new scenarios.

[0013] The local navigation area is a simulation environment built to verify the effectiveness of the algorithm.

[0014] The spatiotemporal feature aggregation module is composed of an independent spatial feature aggregation module and a temporal feature extraction module connected in series.

[0015] The step 1 specifically comprises the following steps:

[0016] 1-1: Define the local navigation area of ​​the surface unmanned boat, set the length value to H and the width value to W;

[0017] 1-2: Initialize the starting coordinates P of the surface unmanned boat STA (x,y), end point coordinates P END (x, y), within the current local navigation area, the coordinates of the unmanned boat at each moment are P(x, y).

[0018] The step 2 specifically includes the following steps:

[0019] 2-1: Determine the random operator and randomly initialize the position coordinates of static obstacles in the blank area Radius Size Randomly selected from mean distribution; s i represents the i-th static obstacle;

[0020] 2-2: For dynamic obstacles, randomly generate their initial position coordinates in the remaining blank area The end point is set as the position coordinates P(x, y) of the surface unmanned boat at the current moment, that is, the end point changes with the movement of the unmanned boat. jrepresents the jth dynamic obstacle.

[0021] The step 3 comprises the following steps:

[0022] 3-1: Based on the type of ship-borne sensors, simulate the working principle and output characteristics of each sensor to generate the current observation signal;

[0023] 3-2: Generate satellite and inertial device signals to provide the ship's own position P(x,y);

[0024] 3-3: Simulate and generate Doppler speed meter signals to provide the ship’s current ground speed V(v x ,v y ).

[0025] 3-4: Simulate and generate laser radar signals to provide the relative distance information D (d1, d2, ..., d N ), where N is the number of laser beams generated when simulating laser radar signals;

[0026] 3-5: Combine the ship's own position information, speed information and obstacle relative distance information to use as the observation signal s in the current environment t = {P(x,y),V(v x ,v y ),D(d1,d2,…,d N )}.

[0027] The step 4 comprises the following steps:

[0028] 4-1: Observation signal s spliced ​​in step 3 t , design a stack structure, stack the signals along the time dimension, and construct spatial feature information S rich in the spatial position changes of obstacles t ={s t-k ,…,s t-1 ,s t}, where s t = {P(x,y),V(v x ,v y ),D(d1,d2,…,d N )}; A rectangular convolutional neural network is used to extract motion features from the spatial feature information.

[0029] 4-2: Based on the feature aggregation of spatial feature information using neural networks, a continuous-time neural network is used to further extract its internal motion-dependent characteristics and obtain the identification characteristics of environmental observation signals in the time dimension; specifically, the continuous-time neural network is composed of sub-networks {f, g, h}, and the three sub-networks share the basic skeleton network structure.

[0030] The step 5 comprises the following steps:

[0031] 5-1: Deterministic value distributed reinforcement learning IQN algorithm is a network framework. By modeling the distribution information of cumulative returns, it uses the return distribution information to guide decision-making, avoiding using the return mean information in all states and ignoring the risk changes in the scene;

[0032] 5-2: Define the action space as the change of acceleration and angular velocity in discrete space α is the acceleration, is the angular velocity;

[0033] 5-3: Determine the reward function r t , define the reward factor for reaching the end point and the penalty factor for colliding with obstacles, define the time penalty factor, and define the end point g-oriented reward function at the current time t

[0034] The step 6 comprises the following steps:

[0035] 6-1: Initialize the deep reinforcement learning network and initialize the input state s t , select action a in the current input state t , execute this action to get the current reward value r t and the next state s t+1 , the experience bar (s t , a t ,r t ,s t+1 ) is stored in the experience replay pool.

[0036] 6-2: Determine the total number of experience replay pools. When the cumulative number of training experience bars exceeds this total number, extract experience bar data in small batches. Use the gradient descent algorithm to calculate the gradient during the back propagation process to complete the network parameter update until the model converges.

[0037] The step 7 comprises the following steps:

[0038] 7-1: The properties of eddies, static obstacles, and dynamic obstacles in the experimental scene remain consistent with those in the training scene, but their positions and numbers are randomly initialized according to the experimental requirements.

[0039] Beneficial effects: Compared with the prior art, the present invention adopts the above technical solution and has the following advantages:

[0040] 1. This invention proposes a method for local anti-pursuit of surface unmanned boats that aggregates spatiotemporal features. From environmental data collected by sensors to decision signals for unmanned boat navigation planning, an end-to-end local path planning network for unmanned boats is constructed. This network structure fully extracts the spatial position changes of continuous observation signals, and further extracts the long-term motion dependency characteristics of obstacles contained in the features through a continuous time network. This enables local collision avoidance and anti-pursuit navigation route planning in high-risk and obstacle-dense scenarios.

[0041] 2. The present invention fully considers the water surface environment and the characteristics of ship-borne sensors, and adds eddy current interference to simulate the impact of the dynamic water surface environment on the ship's speed. The output characteristics of the ship-borne sensors are simulated to generate environmental observation data to ensure that the simulation results are consistent with the front-end sensor input of the ship in the real environment. Compared with the current algorithms that rely more on the location of obstacles and the inference of the location of the body length information, the perception data sources such as lidar used in the present invention have a higher update frequency, and the error transmitted in the obstacle position solution process is smaller, which helps to generate more robust and real-time decision signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a local anti-pursuit method for an unmanned surface boat that aggregates spatiotemporal characteristics according to the present invention.

[0043] Figure 2 It is a schematic diagram of the environment observation state vector constructed by the simulated shipborne sensor of the present invention.

[0044] Figure 3 This is a diagram of the value-distributed reinforcement learning network architecture for aggregating spatiotemporal features of the present invention.

[0045] Figure 4 It is a local anti-pursuit and navigation path planning effect diagram of the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings:

[0047] like Figure 1 As shown, the present invention discloses a local anti-pursuit method for a surface unmanned boat that aggregates spatiotemporal features. In the local path planning process, the working principle and output state of the simulated sensor are used to generate environmental observation signals under multiple information sources, and a stack structure is used to stack environmental observations along the time dimension to obtain state information. Figure 3The network architecture diagram shown includes spatial feature and temporal feature extraction modules, and a fusion value distributed reinforcement learning algorithm to achieve anti-pursuit guidance and navigation path planning for surface unmanned boats in high-risk environments. The method proposed in the present invention mainly serves the navigation path planning module of surface unmanned boats, and provides a real-time and highly secure path planning algorithm for surface unmanned ships in a highly dynamic water surface with strong interference, specifically including the following steps:

[0048] Step 1: Define the scope of the local navigation area, set the starting and ending coordinates of the surface unmanned boat in the area, and randomly generate eddy current signals in the area.

[0049] Step 2: Construct a navigation environment and randomly generate static obstacles of varying sizes and dynamic obstacles of random positions in the blank area.

[0050] Step 3: Based on the type of sensors carried by the real ship, generate a simulated signal that provides information on speed, the ship's own position, and the relative distance to obstacles, and use this to construct the observation signal.

[0051] Step 4: For the observed signal, aggregate the spatial features along the time dimension in a frame-by-frame stacking manner; and input the observed signal frame by frame into the continuous-time neural network to aggregate the temporal features.

[0052] Step 5: Determine the distributed reinforcement learning IQN algorithm as the backbone framework of the navigation planning network and define the action space and reward function.

[0053] Step 6: Use the experience pool to collect experience data during the training process, optimize the network weight parameters with small batches of experience data, and train the deep reinforcement learning model with the experience replay strategy until convergence.

[0054] Step 7: Build an experimental verification scenario, load the converged model parameters, and verify the ship's anti-pursuit and collision avoidance capabilities in the local environment and its generalization capabilities to cope with new scenarios.

[0055] Furthermore, step 1 specifically includes the following steps:

[0056] 1-1: Define the local navigation area of ​​the surface unmanned boat, and set the length value to H and the width value to W.

[0057] 1-2: Initialize the starting coordinates P of the surface unmanned boat STA (x,y), end point coordinates P END (x, y). Within the current local navigation area, the coordinates of the unmanned boat at each moment are P(x, y).

[0058] Furthermore, step 2 specifically includes the following steps:

[0059] 2-1: Determine the random operator and randomly initialize the position coordinates of static obstacles in the blank area Radius Size Randomly selected from a mean distribution.

[0060] 2-2: For dynamic obstacles, randomly generate their initial position coordinates in the remaining blank area The end point is set as the position coordinates P(x, y) of the surface unmanned boat at the current moment, that is, the end point changes continuously with the movement of the unmanned boat.

[0061] Further, step 3 includes the following steps:

[0062] 3-1: Based on the type of ship-borne sensors, simulate the working principle and output characteristics of each sensor to generate the observation signal at the current moment.

[0063] 3-2: Generate satellite and inertial device signals to provide the ship’s own position P(x,y).

[0064] 3-3: Simulate and generate Doppler speed meter signals to provide the ship’s current ground speed V(v x ,v y ).

[0065] 3-4: Simulate and generate laser radar signals to provide the relative distance information D (d1, d2, ..., d N ), where N is the number of laser beams generated when simulating the lidar signal.

[0066] 3-5: Combine the ship's own position information, speed information and obstacle relative distance information to use as the observation signal s in the current environment t = {P(x,y),V(v x ,v y ),D(d1,d2,…,d N )}.

[0067] Further, step 4 includes the following steps:

[0068] 4-1: Observation signal s spliced ​​in step 3 t , design a stack structure, stack the signals along the time dimension, and construct spatial feature information S rich in the spatial position changes of obstacles t ={s t-k ,…,s t-1 ,s t}, where s t = {P(x,y),V(v x ,v y ),D(d1,d2,…,d N)}. A rectangular convolutional neural network is used to extract motion features from the spatial feature information.

[0069] 4-2: Based on the feature aggregation of spatial feature information using neural networks, a continuous-time neural network is used to further extract its internal motion-dependent characteristics and obtain the identification features of environmental observation signals in the time dimension. Specifically, the continuous-time neural network is composed of sub-networks {f, g, h}, and the three sub-networks share the basic skeleton network structure.

[0070] Further, step 5 includes the following steps:

[0071] 5-1: Deterministic value distributed reinforcement learning IQN algorithm is a network framework. It models the distribution information of cumulative returns and uses the return distribution information to guide decision-making, avoiding using the mean return information in all states and ignoring the risk changes in the scenario.

[0072] 5-2: Define the action space as the change of acceleration and angular velocity in discrete space

[0073] 5-3: Determine the reward function r t , define the reward factor for reaching the end point and the penalty factor for colliding with obstacles, define the time penalty factor, and define the end point guidance reward function at the current moment

[0074] Further, step 6 includes the following steps:

[0075] 6-1: Initialize the deep reinforcement learning network and initialize the input state s t , select action a in the current input state t , execute this action to get the current reward value r t and the next state s t+1 , the experience bar (s t ,a t ,r t ,s t+1 ) is stored in the experience replay pool.

[0076] 6-2: Determine the total number of experience replay pools. When the cumulative number of training experience bars exceeds this total number, extract experience bar data in small batches. Use the gradient descent algorithm to calculate the gradient during the back propagation process to complete the network parameter update until the model converges.

[0077] Further, step 7 includes the following steps:

[0078] 7-1: The properties of eddies, static obstacles, and dynamic obstacles in the experimental scene remain consistent with those in the training scene, but their positions and numbers are randomly initialized according to the experimental requirements.

[0079] Example 1

[0080] The present invention relates to local obstacle avoidance technology for surface unmanned vessels, aiming to guide unmanned boats to autonomously plan navigation paths in a surface environment with dense obstacles, high dynamics, and high risks. In the embodiment, by training a deep reinforcement learning network model in a simulated environment and taking the effectiveness verification of the algorithm in a single scenario as an example, the specific steps of local anti-pursuit and path planning of unmanned boats are elaborated in detail, and the relevant parameter configuration and operation process are as follows:

[0081] Step 1: Define the local obstacle avoidance area as 50*50m, set the starting point of the unmanned boat to (5,5), and set the end point of the unmanned boat to (45,45). The length of the unmanned boat is 1.255m, and the width is 0.29m. Randomly initialize the vortex position.

[0082] Step 2: Randomly initialize static obstacles in the blank area, and the obstacle radius follows a uniform distribution of [1,3] m. Randomly initialize the starting coordinates of the dynamic pursuer obstacle, and the pursuer ship is 1 m long and 0.5 m wide.

[0083] Step 3: Build Figure 2 The composite observation vector shown contains the ship's own position provided by satellite and inertial device signals, speed information obtained from the Doppler velocimeter, and relative distance information obtained from the lidar. The stack length is set to 4, and four consecutive frames of observation vectors are stacked as the input of the deep reinforcement learning network.

[0084] Step 4: Send the composite observation signal to Figure 2 In the constructed spatial feature extraction and temporal feature extraction modules, the data dimension is reduced while the spatiotemporal features of environmental observation signals are aggregated, and the output action signals are decided by the value distribution reinforcement learning network.

[0085] Step 5: The action space contains the acceleration change in discrete space [-0.2, 0, 0.2] m / s 2 , angular velocity changes to [-5,0,5]° / s. In the reward function, the reward value for reaching the target is set to 50, the penalty value for collision is set to -100, the time penalty is set to -1, and the difference between the distance to the end point at the previous moment and the distance to the end point at the current moment is used as the sub-reward factor.

[0086] Step 6: Use the experience revisit strategy to train the neural network until convergence.

[0087] Step 7: Load the network parameters trained to convergence in step 6 into the model, randomly generate a local navigation environment, and verify the anti-pursuit capability and navigation path planning capability of the ship in the local environment. Figure 4The experimental results are shown in Figure 1. The orange rectangle represents the dynamic pursuer, the green rectangle represents the surface unmanned boat, and the gray circle represents the static obstacle.

[0088] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0089] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features, characterized in that: The method includes: Step 1: Define the scope of the local navigation area, set the starting and ending coordinates of the surface unmanned boat in the area, and randomly generate eddy current signals in the area; Step 2: Construct a navigation environment and randomly generate static obstacles of different sizes and dynamic obstacles of random positions in the blank area; Step 3: Based on the type of sensors carried by the real ship, generate a simulated signal that provides information on speed, the ship's own position, and the relative distance of obstacles, and use this to construct an observation signal; Step 4: Send the observation signal to the spatiotemporal feature aggregation module to aggregate the spatial features in a frame-by-frame stacking manner along the time dimension; and input the observation signal frame by frame into the continuous time neural network to aggregate the temporal features; Step 5: Determine the distributed reinforcement learning algorithm as the backbone framework of the navigation planning network and define the action space and reward function; Step 6: Use the experience pool to collect experience data during the training process, optimize the network weight parameters with small batches of experience data, and use the experience replay strategy to train the deep reinforcement learning model until convergence; Step 7: Build an experimental verification scenario, load the converged model parameters, and verify the ship's anti-pursuit and collision avoidance capabilities in the local environment and its generalization capabilities to cope with new scenarios.

2. According to the method of claim 1, the local anti-pursuit method of the surface unmanned boat by aggregating spatiotemporal features is characterized in that: The local navigation area is a simulation environment built to verify the effectiveness of the algorithm.

3. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The spatiotemporal feature aggregation module is composed of an independent spatial feature aggregation module and a temporal feature extraction module connected in series.

4. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The step 1 specifically comprises the following steps: 1-1: Define the local navigation area of ​​the surface unmanned boat, set the length value to H and the width value to W; 1-2: Initialize the starting coordinates P of the surface unmanned boat STA (x,y), end point coordinates P END (x, y), within the current local navigation area, the coordinates of the unmanned boat at each moment are P(x, y).

5. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The step 2 specifically includes the following steps: 2-1: Determine the random operator and randomly initialize the position coordinates of static obstacles in the blank area Radius Size Randomly selected from mean distribution; s i represents the i-th static obstacle; 2-2: For dynamic obstacles, randomly generate their initial position coordinates in the remaining blank area The end point is set as the position coordinates P(x, y) of the surface unmanned boat at the current moment, that is, the end point changes with the movement of the unmanned boat. j represents the jth dynamic obstacle.

6. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The step 3 comprises the following steps: 3-1: Based on the type of ship-borne sensors, simulate the working principle and output characteristics of each sensor to generate the current observation signal; 3-2: Generate satellite and inertial device signals to provide the ship's own position P(x,y); 3-3: Simulate and generate Doppler speed meter signals to provide the ship’s current ground speed V(v x ,v y ). 3-4: Simulate and generate laser radar signals to provide the relative distance information D (d1, d2, ..., d N ), where N is the number of laser beams generated when simulating laser radar signals; 3-5: Combine the ship's own position information, speed information and obstacle relative distance information to use as the observation signal s in the current environment t = {P(x,y),V(v x ,v y ),D(d1,d2,…,d N )}.

7. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The step 4 comprises the following steps: 4-1: Observation signal s spliced ​​in step 3 t , design a stack structure, stack the signals along the time dimension, and construct spatial feature information S rich in the spatial position changes of obstacles t ={s t-k ,…,s t-1 ,s t }, where s t = {P(x,y),V(v x ,v y ),D(d1,d2,…,d N )}; A rectangular convolutional neural network is used to extract motion features from the spatial feature information. 4-2: Based on the feature aggregation of spatial feature information using neural networks, a continuous-time neural network is used to further extract its internal motion-dependent characteristics and obtain the identification characteristics of environmental observation signals in the time dimension; specifically, the continuous-time neural network is composed of sub-networks {f, g, h}, and the three sub-networks share the basic skeleton network structure.

8. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The step 5 comprises the following steps: 5-1: Deterministic value distributed reinforcement learning IQN algorithm is a network framework. By modeling the distribution information of cumulative returns, it uses the return distribution information to guide decision-making, avoiding using the return mean information in all states and ignoring the risk changes in the scene; 5-2: Define the action space as the acceleration and angular velocity changes a in discrete space t ={α,ω}; α is the acceleration, is the angular velocity; 5-3: Determine the reward function r t , define the reward factor for reaching the end point and the penalty factor for colliding with obstacles, define the time penalty factor, and define the end point g-oriented reward function at the current time t 9. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1 is characterized in that: The step 6 comprises the following steps: 6-1: Initialize the deep reinforcement learning network and initialize the input state s t , select action a in the current input state t , execute this action to get the current reward value r t and the next state s t+1 , the experience bar (s t ,a t ,r t ,s t+1 ) is stored in the experience replay pool. 6-2: Determine the total number of experience replay pools. When the cumulative number of training experience bars exceeds this total number, extract experience bar data in small batches. Use the gradient descent algorithm to calculate the gradient during the back propagation process to complete the network parameter update until the model converges.

10. The local anti-pursuit method for unmanned surface boats by aggregating spatiotemporal features according to claim 1, characterized in that: Step 7 The following steps are involved: 7-1: The properties of eddies, static obstacles, and dynamic obstacles in the experimental scene remain consistent with those in the training scene, but their positions and numbers are randomly initialized according to the experimental requirements.

Images