Negotiation-based ship cooperation collision avoidance method in marine hybrid navigation scene

Abstract

The invention provides a negotiation-based ship cooperation collision avoidance method in a maritime hybrid navigation scene. The method comprises the following steps: S1, determining negotiation participants, negotiation topics, retention values and utility functions in a hybrid navigation scene; s2, a negotiation communication protocol based on the Speech Act theory is adopted, and negotiation communication primitives and content are defined; s3, adopting a negotiation protocol based on alternate bidding to negotiate ships to sequentially put forward respective collision avoidance schemes; s4, the autonomous ship adopts a negotiation strategy based on a Zeuthen strategy to decide whether to make concession or not, a negotiation process is driven, and a consensus is achieved; and S5, the autonomous ship estimates the retention value of the target ship by applying a Bayesian learning mechanism, and further fits an effect use function. The negotiation-based cooperative collision avoidance method provided by the invention is suitable for a complex marine environment in which a traditional ship and an autonomous ship coexist, and can effectively reduce the collision risk and improve the marine traffic safety and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical fields of offshore mixed navigation scenarios and ship cooperative collision avoidance, and in particular, to a negotiation-based ship cooperative collision avoidance method in an offshore mixed navigation scenario. Background Art

[0002] The technological maturation of autonomous ships, the enlargement of ships, and the scale-up of fleets still have great room for development. For a quite long period of time, the huge technological foundation and market share of traditional ships will not be shaken. The coexistence of autonomous ships and traditional ships is inevitable and long-term, forming an offshore mixed navigation scenario. For autonomous ships, there are significant differences in their degree of autonomy and core decision-making algorithms. At the same time, different drivers also have great differences in ship handling skills, understanding and compliance with rules, and rich navigation experience. Therefore, in such a background, it is extremely easy for ships to have uncoordinated collision avoidance situations. Traditional collision avoidance methods have been proven effective in a single ship type environment, but in the case of the coexistence of autonomous ships and traditional ships, these methods may not be fully applicable. As a new exploration direction, cooperative collision avoidance methods aim to improve the effect of collision avoidance through information sharing and cooperative decision-making among ships. In this method, the intelligent computing and learning capabilities of autonomous ships can be fully utilized, while traditional ships only need to perform simple information interaction, thus avoiding large-scale transformation of their operating systems.

[0003] Centralized cooperative collision avoidance methods require a central coordinator and do not have a wide range of application scenarios. In a distributed framework, each ship can independently formulate its own collision avoidance decision, and then reach an agreement through communication, negotiation, and interaction to achieve cooperative collision avoidance and improve collision avoidance efficiency and navigation safety. Summary of the Invention

[0004] According to the above-mentioned technical problems, a negotiation-based ship cooperative collision avoidance method in an offshore mixed navigation scenario is provided. The present invention clarifies the negotiation participants, negotiation topics, defines and describes the reservation value and utility function, establishes a communication mechanism including negotiation communication primitives and content, uses the alternating offers protocol to clarify the negotiation proposal method, and clarifies the application mechanism of the Zeuthen unilateral concession strategy through the maximum risk acceptance degree, enabling ships to finally reach a collision avoidance consensus. In addition, a unilateral learning mechanism based on the Bayesian method is introduced to enhance the negotiation ability of autonomous ships.

[0005] The technical means adopted by the present invention are as follows:

[0006] A negotiation-based ship cooperative collision avoidance method in an offshore mixed navigation scenario, comprising:

[0007] S1. In a mixed navigation scenario, determine the negotiation participants, negotiation topics, reservation values, and utility functions;

[0008] S2. Adopt a negotiation communication protocol based on the Speech Act theory to define negotiation communication primitives and content;

[0009] S3. Adopt a negotiation protocol based on alternating offers, and the negotiating ships successively propose their respective collision avoidance plans;

[0010] S4. The autonomous ship adopts a negotiation strategy based on the Zeuthen strategy to decide whether to make concessions, drive the negotiation process and reach a consensus;

[0011] S5. The autonomous ship applies a Bayesian learning mechanism to estimate the reservation value of the target ship and further fits it into a utility function.

[0012] Furthermore, step S1 specifically includes:

[0013] S11. Use the Automatic Identification System (AIS) of ships to obtain the position, speed, and heading information of ships, calculate the closest distance of approach and the closest time of approach between ships, compare the closest distance of approach and the closest time of approach with preset safety thresholds, identify pairs of ships that may collide, and determine them as negotiation participants;

[0014] S12. Take the possibility of collision between ships, the situation between ships, and the proposed collision avoidance actions as negotiation topics;

[0015] S13. According to the International Regulations for Preventing Collisions at Sea, determine the avoidance responsibilities of ships, abstract the avoidance responsibilities into the amount of change in heading, and use it as the reservation value of the ships;

[0016] S14. Construct a utility function for autonomous ships considering safety and fit the utility function of traditional ships.

[0017] Furthermore, step S14 specifically includes:

[0018] S141. Use the Sigmod function to map the collision risk degree to the range between [0, 1]. The higher the utility value, the lower the collision risk. The utility function is the remaining collision risk degree after the collision avoidance action, including the following calculation method:

[0019]

[0020] CRI = CR D ×CR T

[0021]

[0022] where CR S represents the spatial collision risk between two ships; CR TIndicates the time collision risk between two ships; CRI indicates the collision risk between two ships; Indicates the utility function of the autonomous ship; DCPA and TCPA respectively indicate the closest distance of approach and the time to the closest point of approach; d1 and d2 respectively indicate the upper and lower bounds of the safe passing distance in space for the ship; t1 and t2 respectively indicate the upper and lower bounds of the safe passing time for the ship; λ determines the steepness of the transition;

[0023] S142. Fit the utility function of traditional ships with a risk-neutral linear function, and assume that the first proposal of traditional ships has the maximum utility value, and the utility value at the reservation value is 0.6.

[0024] Furthermore, step S2 specifically includes:

[0025] S21. Construct a negotiation communication protocol based on the Speech Act theory, and encapsulate the information required to avoid collisions into a structured information set;

[0026] S22. Based on the constructed negotiation communication protocol, define negotiation communication primitives, including message reception, expressing disagreement, confirming acceptance, explicitly rejecting, requesting clarification, verifying information, information sharing, providing suggestions, and making strong demands;

[0027] S23. Based on the constructed negotiation communication protocol, define the communication content, including the navigation information of the ship, the encounter situation, and the collision avoidance decision.

[0028] Furthermore, in step S23, the defined communication content consists of keywords and values, as shown in the following formula:

[0029] Data=$Primitive:Content$

[0030] Communication content=Keyword(Value).

[0031] Furthermore, step S3 specifically includes:

[0032] S31. Construct a negotiation protocol based on alternating offers, and simulate the common "call - response" communication mode in actual maritime collision avoidance;

[0033] S32. The negotiating ships successively propose their respective collision avoidance plans to promote the two parties to reach a collision avoidance consensus through continuous adjustment.

[0034] Furthermore, step S4 specifically includes:

[0035] S41. The autonomous ship adopts the Zeuthen one-way concession strategy and decides whether to make a concession according to its own maximum risk acceptance;

[0036] S42. The ship starts from the most favorable plan for itself and gradually makes concessions towards the plan favorable to the other party, and will never regress.

[0037] Further, in step S5, the autonomous ship continuously updates the estimation of the utility function of the target ship by using the Bayesian learning mechanism to improve the accuracy of the information required for negotiation, specifically including:

[0038] S51. Define the initial estimation of the reservation value range of the autonomous ship for the traditional ship as RVR = {r1, r2,..., r n}, define the probability estimation of the reservation value of the autonomous ship for the traditional ship as p(r i ), and define the conditional probability of the proposal of the traditional ship under the assumption of the autonomous ship as p(q i |r i ), that is, the probability of the proposal q i under each r i .

[0039] S52. Assume that the proposal of the traditional ship is q1, then the probability distribution of the reservation value of the autonomous ship for the traditional ship is updated as:

[0040]

[0041] S53. The estimation of the reservation value of the autonomous ship for the traditional ship is updated as:

[0042]

[0043] S54. In a round of negotiation, the autonomous ship calculates and estimates the maximum risk acceptance degrees of both parties, and the party with the smaller value will modify its proposal and make concessions; taking the autonomous ship as an example, the calculation of its maximum risk acceptance degree in the i-th round is shown in the following formula:

[0044]

[0045] Among them, and respectively represent the utilities of the autonomous ship and the traditional ship under the proposal of the autonomous ship in the i-th round, and respectively represent the utilities of the traditional ship and the autonomous ship under the proposal of the traditional ship in the i-th round, and U(a) and U(c) respectively represent the utility values when the negotiation fails, which are 0.

[0046] Compared with the prior art, the present invention has the following advantages:

[0047] 1. A negotiation-based ship cooperative collision avoidance method in a maritime mixed navigation scenario provided by the present invention effectively solves the problem of ship cooperative collision avoidance in a mixed navigation scenario, improves the current situation of active avoidance of autonomous ships, realizes two-way communication and cooperation between autonomous ships and traditional ships, jointly formulates a collision avoidance plan, not only avoids the occurrence of collision accidents, but also reduces the amount of course change and deceleration amplitude of ships, and improves navigation efficiency.

[0048] 2. The communication mechanism proposed by the negotiation-based ship cooperative collision avoidance method in a maritime mixed navigation scenario provided by the present invention ensures the effectiveness and accuracy of information transmission. The negotiation protocol makes the negotiation process smoother and more efficient. The negotiation strategy not only ensures the convergence of the negotiation process, but also balances the interests of both parties.

[0049] 3. The negotiation-based ship cooperative collision avoidance method in a maritime mixed navigation scenario provided by the present invention applies a Bayesian learning mechanism, which can continuously update the estimation of the reservation value of the target ship, fit the utility function of the target ship, thereby predicting its subsequent behavior, providing a reference for the negotiation process, and improving the negotiation efficiency and success rate.

[0050] Based on the above reasons, the present invention can be widely promoted in the fields of maritime mixed navigation scenarios and ship cooperative collision avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a schematic diagram of the negotiation formation process of a negotiation-based ship cooperative collision avoidance method in a maritime mixed navigation scenario of the present invention.

[0053] Figure 2 It is a schematic diagram of the negotiation protocol and negotiation process described in the present invention.

[0054] Figure 3 It is the negotiation protocol based on alternating offers described in the present invention.

[0055] Figure 4 The application process of the Zeuthen strategy in ship collision avoidance negotiation described in the present invention.

[0056] Figure 5 The unilateral learning model of ship collision avoidance negotiation based on the Zeuthen strategy in ship collision avoidance negotiation described in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0057] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0058] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0059] The present invention provides a negotiation-based ship cooperative collision avoidance method in a mixed navigation scenario at sea, including:

[0060] S1. In a mixed navigation scenario, determine the negotiation participants, negotiation topics, reservation values, and utility functions;

[0061] S2. Adopt a negotiation communication protocol based on the Speech Act theory to define negotiation communication primitives and content;

[0062] S3. Adopt a negotiation protocol based on alternating offers, and the negotiating ships successively propose their respective collision avoidance plans;

[0063] S4. The autonomous ship adopts a negotiation strategy based on the Zeuthen strategy to decide whether to make concessions, drive the negotiation process, and reach a consensus;

[0064] S5. The autonomous ship applies a Bayesian learning mechanism to estimate the reservation value of the target ship and further fit it into a utility function.

[0065] When specifically implemented, as a preferred implementation manner of the present invention, step S1 specifically includes:

[0066] S11. Use the Automatic Identification System (AIS) of ships to obtain the position, speed, and course information of ships, calculate the closest distance of approach (DCPA) and the closest time of approach (TCPA) between ships, compare the closest distance of approach and the closest time of approach with preset safety thresholds, identify ship pairs that may collide, and determine them as negotiation participants;

[0067] S12. Take the possibility of collision between ships, the situation between ships, and the proposed collision avoidance actions as negotiation topics;

[0068] S13. According to the International Regulations for Preventing Collisions at Sea (COLREGs), determine the avoidance responsibilities of ships, abstract the avoidance responsibilities into the amount of change in course, and use it as the reserved value of the ships;

[0069] S14. Construct a utility function for autonomous ships considering safety and fit the utility function of traditional ships.

[0070] In this embodiment, the offshore mixed navigation scenario is specifically an offshore traffic scenario mixed with traditional ships and autonomous ships. Ships judge that there is a current collision risk according to COLREGs and form an uncoordinated collision avoidance scenario, so the ships start to negotiate on this issue. Specifically: as Figure 1 shown, for autonomous ships, identify and track traditional ships, calculate the collision risk degree and initial decision, and then initiate negotiation, which includes the set negotiation protocol and strategy. For traditional ships, the on-duty pilot identifies and tracks autonomous ships, evaluates the current collision risk, makes corresponding decisions, and participates in the negotiation. In multiple rounds of negotiation, both parties reach a consensus and end the negotiation.

[0071] Specifically in implementation, as a preferred implementation manner of the present invention, step S14 specifically includes:

[0072] S141. Use the Sigmod function to map the collision risk degree to the range of [0, 1]. The higher the utility value, the lower the collision risk. The utility function is the remaining collision risk degree after the collision avoidance action, and includes the following calculation methods:

[0073]

[0074]

[0075] Among them, CR S represents the spatial collision risk between two ships; CR T represents the temporal collision risk between two ships; CRI represents the collision risk between two ships; represents the utility function of an autonomous ship; DCPA and TCPA represent the distance of closest point of approach and the time to closest point of approach respectively; d1 and d2 represent the upper and lower bounds of the spatial safe passing of ships respectively; t1 and t2 represent the upper and lower bounds of the temporal safe passing of ships respectively; λ determines the steepness of the transition;

[0076] S142. Fit the utility function of a traditional ship with a risk-neutral linear function, and assume that the first proposal of the traditional ship has the maximum utility value, and the utility value at the reservation value is 0.6.

[0077] In specific implementation, as a preferred implementation manner of the present invention, step S2 specifically includes:

[0078] S21. As Figure 2 shown, construct a negotiation communication protocol based on the Speech Act theory, and encapsulate the information required to avoid collisions into a structured information set;

[0079] S22. Based on the constructed negotiation communication protocol, define negotiation communication primitives, including message reception (Ack), expression of disagreement (Disagree), confirmation of acceptance (Accept), explicit rejection (Reject), request for clarification (Doubt), verification of information (Verify), information sharing (Inform), providing advice (Advise), and making a strong request (Request);

[0080] S23. Based on the constructed negotiation communication protocol, define the communication content, including the navigation information of the ship, the encounter situation, and the collision avoidance decision.

[0081] In specific implementation, as a preferred implementation manner of the present invention, in step S23, the defined communication content is composed of keywords and values, as shown in the following formula:

[0082] Data=$Primitive:Content$

[0083] Communication content=Keyword(Value).

[0084] In specific implementation, as a preferred implementation manner of the present invention, step S3 specifically includes:

[0085] S31. As Figure 3 shown, construct a negotiation protocol based on alternating offers, and simulate the common "call - response" communication mode in actual maritime collision avoidance;

[0086] S32. The negotiating ships successively propose their respective collision avoidance plans to promote the two parties to reach a collision avoidance consensus in continuous adjustment.

[0087] In specific implementation, as a preferred implementation manner of the present invention, step S4 specifically includes:

[0088] S41. As shown in Figure 4 , the autonomous ship adopts the Zeuthen one-way concession strategy and decides whether to make a concession according to its own maximum risk acceptance; (Based on the Zeuthen one-way concession strategy, the ship in the negotiation process will decide whether to make a concession according to its expected revenue and the tolerated risk)

[0089] S42. The ship starts from the plan that is most favorable to itself and gradually makes concessions to the plan that is favorable to the other party, and will never go back.

[0090] In specific implementation, as a preferred implementation manner of the present invention, in step S5, the autonomous ship uses the Bayesian learning mechanism to continuously update the estimation of the utility function of the target ship and improve the accuracy of the information required for negotiation, specifically including:

[0091] S51. Define the initial estimation of the reservation value range of the autonomous ship for the traditional ship as RVR = {r1, r2,..., r n}, define the probability estimation of the reservation value of the autonomous ship for the traditional ship as p(r i ), and define the conditional probability of the proposal of the traditional ship under the assumption of the autonomous ship as p(q i |r i ), that is, the probability of the proposal q i under each r i ;

[0092] S52. Assume that the proposal of the traditional ship is q1, then the probability distribution of the reservation value of the autonomous ship for the traditional ship is updated as:

[0093]

[0094] S53. The estimation of the reservation value of the autonomous ship for the traditional ship is updated as:

[0095]

[0096] S54. In a round of negotiation, the autonomous ship calculates and estimates the maximum risk acceptance of both parties, and the party with the smaller value will modify its proposal and make a concession; taking the autonomous ship as an example, the calculation of its maximum risk acceptance degree in the i-th round is shown in the following formula:

[0097]

[0098] Where and respectively represent the utilities of the autonomous ship and the traditional ship under the proposal of the autonomous ship in the i-th round, and represent the utilities of the traditional ship and the autonomous ship under the traditional ship's proposal in the $i$-th round respectively. $U(a)$ and $U(c)$ represent the respective utility values when the negotiation fails, which are 0.

[0099] In this embodiment, the autonomous ship applies the Bayesian learning mechanism to continuously update the estimation of the reservation value of the target ship, as Figure 5 shown. According to the proposal and actions of the target ship, calculate the conditional probability, update the posterior probability of the target ship's reservation value, further fit the utility function of the target ship, predict the subsequent behavior of the target ship, and improve the negotiation ability. Specifically: The autonomous ship presets its own utility function and has prior knowledge of the autonomous ship. During the negotiation, when the autonomous ship receives the proposal from the target ship, it is regarded as obtaining posterior knowledge, updates the prior knowledge according to the Bayesian learning mechanism, and calculates the maximum risk acceptance degree using the Zeuthen strategy to decide whether to make concessions. And the autonomous ship will decide whether to make a new proposal according to the other party's proposal. The negotiation process can be regarded as a set of dynamic proposal sequences, and the last set of proposals is the negotiation solution.

[0100] Finally, it should be noted that: The above embodiments are only used to illustrate the technical solutions of the present invention, not to limit it; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A ship cooperative collision avoidance method based on negotiation in a mixed maritime navigation scenario, characterized in that: include: S1. In the mixed navigation scenario, determine the negotiation participants, negotiation topics, reservation values, and utility functions; S2. Adopt the negotiation communication protocol based on Speech Act theory and define the negotiation communication primitives and content; S3. A negotiation protocol based on round-robin bidding is adopted, and the negotiating ships propose their own collision avoidance plans in turn; S4, the autonomous ship adopts a negotiation strategy based on the Zeuthen strategy to decide whether to make concessions, drive the negotiation process and reach a consensus; S5. The autonomous ship applies the Bayesian learning mechanism to estimate the retention value of the target ship and further fits the utility function.

2. According to the method for ship cooperative collision avoidance based on negotiation in a mixed navigation scenario at sea according to claim 1, it is characterized in that: Step S1 specifically includes: S11. Using the ship automatic identification system to obtain the position, speed and heading information of the ships, calculate the closest encounter distance and the closest encounter time between the ships, compare the closest encounter distance and the closest encounter time with the preset safety threshold, identify the ship pairs that may collide, and determine them as negotiation participants; S12. The possibility of collision between ships, the situation between ships, and the proposed collision avoidance actions are the negotiation topics; S13. According to the International Regulations for Preventing Collisions at Sea, the avoidance responsibility of the ship is determined, and the avoidance responsibility is abstracted into the change in course as the retention value of the ship; S14. Construct a utility function of an autonomous ship based on safety considerations and fit the utility function of a traditional ship.

3. The method for ship cooperative collision avoidance based on negotiation in a mixed maritime navigation scenario according to claim 2, characterized in that: Step S14 specifically includes: S141. Use the Sigmod function to map the collision risk to [0,1]. The higher the utility value, the lower the collision risk. The utility function is the remaining collision risk after the collision avoidance action, including the following calculation method: CRI=CR D ×CR T U OSAS =1-CRI Among them, CR S Represents the spatial collision risk between two ships; CR T represents the time collision risk of two ships; CRI represents the collision risk of two ships; represents the utility function of the autonomous ship; DCPA and TCPA represent the closest encounter distance and the closest encounter time, respectively; d1 and d2 represent the upper and lower bounds of the safe encounter of ships in space, respectively; t1 and t2 represent the upper and lower bounds of the safe encounter of ships in time, respectively; λ determines the steepness of the transition; S142. Fit the utility function of the traditional ship with a risk-neutral linear function, and make the first proposal of the traditional ship have the maximum utility value, and the utility value at the reserved value is 0.

6.

4. The method for ship cooperative collision avoidance based on negotiation in a mixed maritime navigation scenario according to claim 1, characterized in that: Step S2 specifically includes: S21. Construct a negotiation communication protocol based on Speech Act theory to encapsulate the information required to avoid collision into a structured information set; S22. Based on the constructed negotiation communication protocol, define negotiation communication primitives, including message reception, expression of disagreement, confirmation of acceptance, explicit rejection, request for clarification, verification of information, information sharing, provision of suggestions, and strong demands; S23. Based on the constructed negotiation communication protocol, define the communication content, including the ship's navigation information, encounter situation, and collision avoidance decision.

5. The method for ship cooperative collision avoidance based on negotiation in a mixed maritime navigation scenario according to claim 1, characterized in that: In step S23, the defined communication content is composed of keywords and values, as shown in the following formula: Data = $Primitive:Content$ Communication content=Keyword(Value).

6. The method for ship cooperative collision avoidance based on negotiation in a mixed maritime navigation scenario according to claim 1, characterized in that: Step S3 specifically includes: S31. Construct a negotiation protocol based on bidding in turns to simulate the "call-response" communication mode commonly seen in actual maritime collision avoidance; S32. The negotiating ships shall propose their own collision avoidance plans in turn to promote the two parties to reach a consensus on collision avoidance through continuous adjustments.

7. The method for ship cooperative collision avoidance based on negotiation in a mixed maritime navigation scenario according to claim 1, characterized in that: Step S4 specifically includes: S41. Autonomous ships adopt the Zeuthen unilateral concession strategy and decide whether to make concessions based on their maximum risk acceptance. S42. The ship shall start from the plan that is most favorable to itself and gradually make concessions to the plan that is favorable to the other party and will never retreat.

8. The method for ship cooperative collision avoidance based on negotiation in a mixed navigation scenario at sea according to claim 1, characterized in that: In step S5, the autonomous ship continuously updates the estimate of the target ship's utility function using the Bayesian learning mechanism to improve the accuracy of the information required for negotiation, including: S51. Define the initial estimate of the range of autonomous ship retention value for conventional ships as RVR = {r1, r2, ..., r n }, the probability estimate of the retention value of autonomous ships to traditional ships is defined as p(r i ), the conditional probability of the proposed traditional ship under the autonomous ship assumption is defined as p(q i |r i ), that is, each r i Next suggestion i probability; S52. Assuming that the proposal of the traditional ship is q1, the probability distribution of the reserved value of the autonomous ship to the traditional ship is updated as: S53. The estimated retention value of autonomous ships to conventional ships is updated to: S54. In a round of negotiation, the autonomous ship calculates and estimates the maximum risk acceptance of both parties. The party with the smaller value will modify its proposal and make concessions. Taking the autonomous ship as an example, the calculation of its maximum risk acceptance in the i-th round is as follows: in, and denote the utility of autonomous ships and traditional ships under the autonomous ship proposal in round i, respectively, and They represent the utilities of the traditional ship and the autonomous ship under the proposal of the traditional ship in the i-th round, respectively. U(a) and U(c) represent their respective utility values ​​when the negotiation fails, which is 0.

Images