CN106845625A - A kind of interactive output intent and robot for robot - Google Patents
A kind of interactive output intent and robot for robot Download PDFInfo
- Publication number
- CN106845625A CN106845625A CN201611199607.2A CN201611199607A CN106845625A CN 106845625 A CN106845625 A CN 106845625A CN 201611199607 A CN201611199607 A CN 201611199607A CN 106845625 A CN106845625 A CN 106845625A
- Authority
- CN
- China
- Prior art keywords
- slave computer
- instruction
- robot
- priority
- execution priority
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
Abstract
The invention discloses a kind of interactive output intent and robot for robot.Methods described includes:Obtain multi-modal input information and parse, the slave computer instruction of the multi-modal interaction output of generation correspondence;It is the corresponding execution priority of the slave computer instructions match, current all slave computer instructions not sent are ranked up according to the execution priority;Robot system slave computer is arrived according to the slave computer instruction is sequentially output to the ranking results that all slave computers not sent are instructed;Slave computer performs the slave computer instruction and carries out corresponding multi-modal output.Method according to the invention it is possible to the order of transmission instructed according to actual interaction scenario reasonable arrangement slave computer, so as to ensure that execution priority slave computer instruction high can preferentially be sent to slave computer and be performed as early as possible.The logic of slave computer execution has thus been effectively ensured, so as to ensure the perfect realization of robot application function, and then the Consumer's Experience of robot has been improved.
Description
Technical field
The present invention relates to robot field, and in particular to a kind of interactive output intent and robot for robot.
Background technology
With continuing to develop for robot technology, the increasing of intelligent robot is applied to the daily production of the mankind
In life.With the continuous upgrading of intelligent robot hardware device, the function of robot also becomes increasingly complex, corresponding robot
Runtime data treating capacity is also continued to increase.A most direct embodiment is exactly, in robot running, robot system
The command quantity for being generated in the internal unit time and being transmitted is continuously increased.Especially, possessing host computer and slave computer structure
In robot system, in the interaction of host computer and slave computer, host computer needs to be sent to slave computer and holds in the unit interval
Capable slave computer instruction is continuously increased.
With the continuous upgrading of robot system disposal ability, in the implementation process of some more complicated application of function,
The execution action that robot is faced is more, it is difficult to the coherent execution for realizing each action, this has just ultimately resulted in machine
People's application function can not be realized perfectly, so as to leverage Consumer's Experience.
The content of the invention
The invention provides a kind of interactive output intent for robot, methods described includes:
Obtain multi-modal input information and parse, the slave computer instruction of the multi-modal interaction output of generation correspondence;
It is the corresponding execution priority of the slave computer instructions match, is not sent out currently all according to the execution priority
The slave computer instruction sent is ranked up;
Machine is arrived according to the slave computer instruction is sequentially output to the ranking results that all slave computers not sent are instructed
Device people's system slave computer;
Slave computer performs the slave computer instruction and carries out corresponding multi-modal output.
In one embodiment, current all slave computer instructions not sent are arranged according to the execution priority
Sequence, wherein:
The slave computer instruction that will be currently generated adds slave computer instruction set;
Prioritization is carried out to all of slave computer instruction in the instruction set.
Slave computer instruction is deleted from the instruction set after output priority highest slave computer is instructed.
In one embodiment, current all slave computer instructions not sent are arranged according to the execution priority
Sequence, wherein, based on the execution priority, the generation time instructed according to the slave computer and the slave computer are instructed
Implementing precondition be ranked up, including:
In two slave computer instructions, before the instruction of one of slave computer is for the execution of another slave computer instruction
When carrying, will be come in forward sequence as the instruction of the slave computer of implementing precondition;
In two slave computer instructions in the absence of implementing precondition relation, when the execution priority is identical, press
Sequencing according to the slave computer instruction generation time is ranked up.
In one embodiment, it is the corresponding execution priority of the slave computer instructions match, wherein:
The interaction mode of current robot and/or the interaction demand of user are determined according to the multi-modal input information;
The execution priority of the slave computer instruction is determined based on the interaction mode and/or the interaction demand.
In one embodiment, it is the corresponding execution priority of the slave computer instructions match, wherein:
Corresponding execution priority levels list is instructed according to default slave computer in system, to slave computer instruction
With corresponding execution priority.
The invention allows for a kind of intelligent robot, the robot includes:
Input acquisition module, it is configured to obtain multi-modal input information;
Directive generation module, it is configured to the parsing multi-modal input information, the multi-modal interaction output of generation correspondence
Slave computer is instructed;
Priority match module, it is configured to be the corresponding execution priority of the slave computer instructions match;
Instruction reorder module, it is configured to refer to current all slave computers not sent according to the execution priority
Order is ranked up;
Command output module, it is configured to defeated successively according to the ranking results instructed to all slave computers not sent
Go out the slave computer instruction;
Slave computer, its slave computer instruction for being configured to perform the command output module output carries out corresponding multi-modal defeated
Go out.
In one embodiment, the instruction reorder module includes:
Instruction set memory cell, its slave computer instruction for being configured to preserve instruction set and will be currently generated adds the next
Machine instruction set, also, slave computer instruction is deleted from the instruction set after output priority highest slave computer is instructed;
Instruction set sequencing unit, it is configured to carry out prioritization to all of slave computer instruction in the instruction set.
In one embodiment, the instruction reorder module is additionally configured to based on the execution priority, according to described
The generation time of slave computer instruction and the implementing precondition of slave computer instruction are ranked up, wherein:
In two slave computer instructions, before the instruction of one of slave computer is for the execution of another slave computer instruction
When carrying, will be come in forward sequence as the instruction of the slave computer of implementing precondition;
In two slave computer instructions in the absence of implementing precondition relation, when the execution priority is identical, press
Sequencing according to the slave computer instruction generation time is ranked up.
In one embodiment, the priority match module includes:
Interactive information collecting unit, its interaction for being configured to determine according to the multi-modal input information current robot
State and/or the interaction demand of user;
Priority determining unit, it is configured to the interaction mode and/or the interaction demand determines the bottom
The execution priority of machine instruction.
In one embodiment, the priority match module includes:
Priority list storage unit, default slave computer instructs corresponding execution priority during it is configured to preservation system
Levels list;
Priority determining unit, it is configured to according to the execution priority levels list to the slave computer instructions match
Corresponding execution priority.
Method according to the invention it is possible to the order of transmission instructed according to actual interaction scenario reasonable arrangement slave computer, from
And ensureing execution priority slave computer instruction high can preferentially be sent to slave computer and be performed as early as possible.Thus it is effectively ensured
The logic that slave computer is performed, so as to ensure the perfect realization of robot application function, and then improves the user's body of robot
Test.
Further feature of the invention or advantage will be illustrated in the following description.Also, Partial Feature of the invention or
Advantage will be become apparent by specification, or be appreciated that by implementing the present invention.The purpose of the present invention and part
Advantage can be realized or obtained by specifically noted step in specification, claims and accompanying drawing.
Brief description of the drawings
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for specification, with reality of the invention
Apply example to be provided commonly for explaining the present invention, be not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is method flow diagram according to an embodiment of the invention;
Fig. 2~Fig. 5 is the partial process view of method according to embodiments of the present invention;
Fig. 6 and Fig. 7 are robot system architecture's sketches according to embodiments of the present invention;
Fig. 8 and Fig. 9 are robot system part-structure sketches according to embodiments of the present invention.
Specific embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, implementation personnel of the invention whereby
Can fully understand how application technology means solve technical problem for the present invention, and reach technique effect implementation process and according to
The present invention is embodied according to above-mentioned implementation process.If it should be noted that do not constitute conflict, each embodiment in the present invention
And each feature in each embodiment can be combined with each other, the technical scheme for being formed protection scope of the present invention it
It is interior.
With continuing to develop for robot technology, the increasing of intelligent robot is applied to the daily production of the mankind
In life.With the continuous upgrading of intelligent robot hardware device, the function of robot also becomes increasingly complex, corresponding robot
Runtime data treating capacity is also continued to increase.A most direct embodiment is exactly, in robot running, robot system
The command quantity for being generated in the internal unit time and being transmitted is continuously increased.Especially, possessing host computer and slave computer structure
In robot system, in the interaction of host computer and slave computer, host computer needs to be sent to slave computer and holds in the unit interval
Capable slave computer instruction is continuously increased.
With the continuous upgrading of robot system disposal ability, in the implementation process of some more complicated application of function,
The execution action that robot is faced is more, it is difficult to the coherent execution for realizing each action, this has just ultimately resulted in machine
People's application function can not be realized perfectly, so as to leverage Consumer's Experience.
Regarding to the issue above, the present invention proposes a kind of interactive output intent for robot.
In the actual moving process of robot, robot coherent cannot realize the main of the execution of each action
Reason is:The host computer of robot generates a large amount of slave computers for needing slave computer to perform and instructs simultaneously or in a short time,
Due to (performing one every time) that slave computer instruction typically sequentially sends (send one every time) and sequentially carries out, therefore when upper
Logic exception occurs in the order of transmission of position machine transmission slave computer instruction, and (the slave computer instruction for being for example badly in need of execution at once is arranged to
Longer latency is needed to be sent after being instructed with the slave computer of temporary respite) when, it necessarily causes the execution of slave computer different
Often.
Based on above-mentioned analysis, in an embodiment of the present invention, when simultaneously there is a plurality of slave computer to be sent and instruct, on
Position machine is not that the sequencing (or according to random sequence) generated according to it is transmitted, but first it is carried out to be based on holding
The sequence of row major level, is transmitted according to ranking results so that the slave computer of execution priority (being badly in need of performing at once) higher
Instruction can arrive first at slave computer and be performed, so as to ensure the logic that slave computer is performed, and then ensure robot application
The perfect realization of function, improves the Consumer's Experience of robot.
Next the detailed process of method according to embodiments of the present invention is described in detail based on accompanying drawing, in the flow chart of accompanying drawing
The step of showing can perform in comprising the such as one group computer system of computer executable instructions.Although in flow charts
The logical order of each step is shown, but in some cases, can be performing shown different from order herein or retouch
The step of stating.
As shown in figure 1, in one embodiment, robot (host computer of robot system) obtains multi-modal input letter first
Breath (step S100);Then the multi-modal input information is parsed to determine to respond the multi-modal interaction output of the multi-modal input information
(step S110);Ultimately produce to should it is multi-modal interaction output slave computer instruct (step S120).
Next, host computer is not that the slave computer instruction of generation directly is sent into slave computer immediately to perform, but it is
The corresponding execution priority (step S130) of slave computer instructions match, according to execution priority to current all bottoms not sent
Machine instruction is ranked up (step S140);Then it is sequentially output down according to the ranking results that all slave computers not sent are instructed
Robot system slave computer (step S150) is arrived in position machine instruction;Last slave computer execution slave computer instruction carries out corresponding multi-modal
Output (step S160).
In above process, slave computer instruction is ranked up according to execution priority before slave computer instruction is sent,
This ensures that execution priority slave computer instruction high (the slave computer instruction that needs are immediately performed) can preferentially be sent to
Slave computer is simultaneously performed as early as possible.The logic of slave computer execution is thus effectively ensured, so as to ensure robot application function
Perfect realization, and then improve the Consumer's Experience of robot.
Further, in an embodiment of the present invention, to all slave computers not sent by the way of instruction set sequence
Instruction is ranked up.Specifically, in one embodiment, the slave computer that will be currently generated first after new slave computer instruction is generated
Instruction adds slave computer instruction set (all slave computer instructions not sent for generating before have been preserved in the instruction set);Then
Prioritization is carried out to all of slave computer instruction in instruction set.
When slave computer instruction is exported to slave computer, output order concentrates the slave computer of tagmeme most forward (highest priority)
Instruction, also, slave computer instruction is deleted from instruction set after the instruction is output.
In one embodiment, the generation transmission process of slave computer instruction can be divided into two relatively independent flows.
First it is the generating process of slave computer instruction, as shown in Fig. 2 in one embodiment, the host computer of robot system
Multi-modal input information (step S200) is obtained first;Then the multi-modal input information is parsed to determine to respond the multi-modal input
Multi-modal interaction output (step S210) of information;Then generate to should it is multi-modal interaction output slave computer instruct (step
S220);Instruction is added to the newly-generated corresponding priority (step S230) of slave computer instructions match and by slave computer instruction
Collection (step S240);The sequence based on execution priority finally is carried out to the slave computer instruction in instruction set.
By taking a specific application as an example, it is assumed that there are and the execution priority of A1~A10 (the execution priority highest of A1, it is excellent
First level grade setting is descending).In an interaction cycle, robot host computer generates bottom according to multi-modal input information
Machine instructs B1, and is its matching execution priority A4, in adding it to instruction set.Assuming that now others do not send
Slave computer is instructed, then instruction set is represented by (B1 (A4)).Next, in next interaction cycle, robot host computer root
Slave computer instruction B2 is generated according to multi-modal input information, and is its matching execution priority A5, in adding it to instruction set.
Assuming that now slave computer instruction B1 is not transmitted, then instruction set is represented by (B1 (A4), B2 (A5)).Next,
In next interaction cycle, robot host computer generates slave computer instruction B3 according to multi-modal input information, and is it
With execution priority A1, in adding it to instruction set.Assuming that now slave computer instruction B1 is not transmitted, then instruct
Collection is represented by (B3 (A4), B1 (A4), B2 (A5)).The current instruction set of correspondence, the transmission order of slave computer instruction just should
It is B3, B1, B2.
Followed by the transmission process of slave computer instruction.As shown in figure 3, when needing to send slave computer instruction, robot
The host computer of system extracts slave computer instruction (step S300) that most forward (execution priority highest) is ranked in instruction set first;
Then the instruction that will be extracted is sent to slave computer (step S310);Then judge that current instruction sends whether operation succeeds
(step S320);If it fails, then return to step S300, sends the instruction again;If it succeeds, being arranged in deleting instruction set
Most forward slave computer instruction (instruction being successfully transmitted) (step S330) in position.
Further, in order to prevent the host computer when slave computer has not carried out completion current slave computer instruction from constantly sending out
The slave computer instruction congestion sent new slave computer to instruct and cause.In one embodiment, host computer is needed before sending slave computer instruction
Verify slave computer state.
Specifically, as shown in figure 4, whether the host computer of robot system first determines whether can currently send slave computer instruction
(whether slave computer is in the idle condition of acceptable new command) (step S400);If it cannot send (slave computer is busy)
Continue waiting for and return to step S400;If can send, ranked most forward (execution priority highest) in extraction instruction set
Slave computer instructs (step S410);Then the instruction that will be extracted is sent to slave computer (step S420);Then judge current
Whether instruction sends operation successful (step S430);If it fails, then return to step S410, sends the instruction again;If
Success, then rank most forward slave computer instruction (instruction being successfully transmitted) (step S440) and return in deletion instruction set
Step S400 judges whether to continue to send next slave computer instruction.
It is corresponding, in one embodiment, as shown in figure 5, the slave computer of robot system judges that whether the state of itself may be used
(step S500) is instructed to perform new slave computer;When currently cannot temporarily receive new slave computer instruction, feedback host computer
The busy condition (step S550) and return to step S500 of itself repeat to judge that oneself state is (after Fixed Time Interval or current
It is carrying out after the completion of slave computer instruction execution).
When can currently receive new slave computer instruction, the idle condition (step S510) of feedback host computer itself;On
Position machine determines that slave computer can receive new command (step 400 shown in Fig. 4) after receiving the feedback, sends new slave computer and refers to
Make (step 410,420 shown in Fig. 4).Slave computer receives new slave computer instruction (step 520), and the feedback after receiving
Host computer is received successfully (step S530).Then slave computer performs slave computer instruction (step S540) for receiving, and is performing
Finish rear return to step S500 and judge whether new slave computer instruction itself can be received.
Further, in step S530, feedback host computer is received into after slave computer receives new slave computer instruction
Work(.Host computer judges that current instruction sends operation and runs succeeded (step 430 shown in Fig. 4) according to the feedback of slave computer.If
Slave computer is not received by slave computer instruction or is not received by complete slave computer instruction, then do not perform step S530 and (do not send out
Go out feedback).Host computer is not received by the feedback of slave computer and then illustrates currently sending in slave computer instruction Fixed Time Interval
Instruction send operation perform failure.
Further, in the present invention, it is ensured that one of key point of logic that slave computer is performed is under to be sent
The sequence of position machine instruction, specifically, the correct execution priority of slave computer instructions match as to be sent.Specifically, one
In embodiment, the interaction mode of current robot and/or the interaction demand of user are determined according to multi-modal input information first;
It is then based on interaction mode and/or interaction demand determines the execution priority of the slave computer instruction.
For example, it is assumed that in the application scenario of a certain robot, robot random autonomic activities in an idle state.Herein
In scene, specifically, it needs the slave computer for performing to instruct including:
Operational order (for example realize looking about, move around the instruction of behavior) for carrying out random autonomic activities;
Collection user behavior information, the monitoring user instruction that newly interaction is indicated (for example gathers user's face information, camera
Tracking user's face movement).
It is independent behaviour in an idle state in view of current robot, then the new command for responding user in time is most
Preferential option, therefore in the slave computer instruction that above-mentioned needs are performed, user behavior information is gathered, newly interaction refers to monitoring user
The instruction shown has highest execution priority.That is, when the instruction for realizing looking about is in instruction set, if newly
The instruction of camera tracking user's face movement is generated, then the preferential instruction for performing camera tracking user's face movement.
Because under actual man-machine interaction scene, the interaction mode and interaction demand of robot are considerably complicated changeable
, determine that the execution priority that slave computer is instructed certainly will need substantial amounts of number by the analysis to interaction mode and interaction demand
Operated according to treatment.It is possible to cause the blunt of robot reaction when processor performance is not enough.Even, in data collection and analysis
Execution priority matching error is also resulted in during error and performs confusion so as to ultimately result in slave computer.
For above-mentioned situation, in an embodiment of the present invention, construction priority-level list in advance, for different bottoms
Machine operational order pre-defines its execution priority.In execution priority corresponding for slave computer instructions match, according to system
In default slave computer instruct corresponding execution priority levels list, to the corresponding execution priority of slave computer instructions match.
Further, because under actual man-machine interaction scene, the interaction mode and interaction demand of robot are phases
When complicated and changeable, therefore in some interaction scenarios, fixed execution priority can not accurately reflect slave computer instruction and hold
Capable reasonable sequencing.
Therefore, in one embodiment, current all slave computer instructions not sent are arranged according to execution priority
During sequence, based on execution priority, the implementing precondition that the generation time instructed according to slave computer and slave computer are instructed is carried out
Sequence.Specifically, it includes:
In two slave computer instructions, when the instruction of one of slave computer is the implementing precondition of another slave computer instruction
When, will be come in forward sequence as the instruction of the slave computer of implementing precondition;
In the two slave computers instruction in the absence of implementing precondition relation, when execution priority is identical, according to slave computer
The sequencing of generation time is instructed to be ranked up.
To sum up, method according to the invention it is possible to the transmission time instructed according to actual interaction scenario reasonable arrangement slave computer
Sequence, so as to ensure that execution priority slave computer instruction high (the slave computer instruction that needs are immediately performed) can preferentially be sent to down
Position machine is simultaneously performed as early as possible.The logic of slave computer execution is thus effectively ensured, so as to ensure robot application function
Perfection is realized, and then improves the Consumer's Experience of robot.
Further, the method according to the invention, the invention allows for a kind of intelligent robot.As shown in fig. 6, one
In embodiment, robot includes:
Input acquisition module 610, it is configured to obtain multi-modal input information;
Directive generation module 620, it is configured to parse multi-modal input information, under the multi-modal interaction output of generation correspondence
Position machine instruction, wherein multi-modal interactive output matching responds multi-modal input information;
Priority match module 630, it is configured to be the corresponding execution priority of slave computer instructions match;
Instruction reorder module 640, its be configured to according to execution priority current all slave computers not sent are instructed into
Row sequence;
Command output module 650, it is configured to defeated successively according to the ranking results instructed to all slave computers not sent
Go out slave computer instruction;
Slave computer 602, its slave computer instruction for being configured to the output of execute instruction output module 650 carries out corresponding multi-modal
Output.
Further, in one embodiment, input acquisition module 610, directive generation module 620, priority match module
630th, instruction reorder module 640 and command output module 650 are subordinated to the host computer 601 of robot system.
Further, as shown in fig. 7, in one embodiment, instruction reorder module 740 includes instruction set memory cell 741
And instruction set sequencing unit 742.Specifically:Input acquisition module 710 obtains multi-modal input information;Directive generation module
720 generation slave computer instructions;Priority match module 730 is the corresponding execution priority of slave computer instructions match;Instruction set is deposited
The slave computer instruction that storage unit 741 preserves instruction set and will be currently generated adds slave computer instruction set;Instruction set sequencing unit 742
Prioritization is carried out to all of slave computer instruction in instruction set;Command output module 750 will rank most forward in instruction set
Slave computer instruction output to slave computer 702;Instruction set memory cell 741 is in the output slave computer instruction of command output module 750
The instruction is deleted from instruction set afterwards;Slave computer 702 performs the slave computer instruction for receiving.
Further, in one embodiment, priority match module is true by current interaction mode and/or interaction demand
Determine the execution priority of slave computer instruction.Specifically, as shown in figure 8, priority match module 830 gathers single comprising interactive information
Unit 831 and priority confirmation unit 832.
Wherein:Input acquisition module 810 obtains multi-modal input information;The generation slave computer instruction of directive generation module 820;
Interactive information collecting unit 831 (in the present embodiment, is got according to multi-modal input information using input acquisition module 810
Multi-modal input information) determine the interaction mode of current robot and/or the interaction demand of user;Priority determining unit
832 interaction modes confirmed based on interactive information collecting unit 831 and/or interaction demand determine instruction generation module 820 are generated
Slave computer instruction execution priority.
Further, in one embodiment, priority match module is by execution priority levels list set in advance
Determine the execution priority of slave computer instruction.Specifically, as shown in figure 9, priority match module 930 is protected comprising priority list
Memory cell 931 and priority determining unit 932.
Wherein:Input acquisition module 910 obtains multi-modal input information;The generation slave computer instruction of directive generation module 920;
Default slave computer instructs corresponding execution priority levels list in the preservation system of priority list storage unit 931;Preferentially
Level determining unit 932 is based on the execution priority levels list determine instruction generation mould that priority list storage unit 931 is preserved
The execution priority of the slave computer instruction of the generation of block 920.
Further, in one embodiment, instruction reorder module is additionally configured to based on execution priority, according to bottom
The generation time of machine instruction and the implementing precondition of slave computer instruction are ranked up, wherein:
In two slave computer instructions, when the instruction of one of slave computer is the implementing precondition of another slave computer instruction
When, will be come in forward sequence as the instruction of the slave computer of implementing precondition;
In two slave computer instructions in the absence of implementing precondition relation, when execution priority is identical, under
The sequencing of position machine instruction generation time is ranked up.
While it is disclosed that implementation method as above, but described content is only to facilitate understanding the present invention and adopting
Implementation method, is not limited to the present invention.Method of the present invention can also have other various embodiments.Without departing substantially from
In the case of essence of the present invention, those of ordinary skill in the art work as can make various corresponding changes or change according to the present invention
Shape, but these corresponding changes or deformation should all belong to scope of the claims of the invention.
Claims (10)
1. a kind of interactive output intent for robot, it is characterised in that methods described includes:
Obtain multi-modal input information and parse, the slave computer instruction of the multi-modal interaction output of generation correspondence;
It is the corresponding execution priority of the slave computer instructions match, all is not sent to current according to the execution priority
The slave computer instruction is ranked up;
Instructed to robot according to the slave computer is sequentially output to the ranking results that all slave computers not sent are instructed
System slave computer;
Slave computer performs the slave computer instruction and carries out corresponding multi-modal output.
2. method according to claim 1, it is characterised in that all do not sent to current according to the execution priority
The slave computer instruction is ranked up, wherein:
The slave computer instruction that will be currently generated adds slave computer instruction set;
Prioritization is carried out to all of slave computer instruction in the instruction set.
Slave computer instruction is deleted from the instruction set after output priority highest slave computer is instructed.
3. method according to claim 1, it is characterised in that all do not sent to current according to the execution priority
Slave computer instruction is ranked up, wherein, based on the execution priority, during the generation instructed according to the slave computer
Between and the slave computer instruction implementing precondition be ranked up, including:
In two slave computer instructions, when the instruction of one of slave computer is the implementing precondition of another slave computer instruction
When, will be come in forward sequence as the instruction of the slave computer of implementing precondition;
In two slave computer instructions in the absence of implementing precondition relation, when the execution priority is identical, according to institute
The sequencing for stating the slave computer instruction generation time is ranked up.
4. method according to claim 1, it is characterised in that performed for the slave computer instructions match is corresponding preferential
Level, wherein:
The interaction mode of current robot and/or the interaction demand of user are determined according to the multi-modal input information;
The execution priority of the slave computer instruction is determined based on the interaction mode and/or the interaction demand.
5. method according to claim 1, it is characterised in that performed for the slave computer instructions match is corresponding preferential
Level, wherein:
Corresponding execution priority levels list is instructed according to default slave computer in system, to the slave computer instructions match pair
The execution priority answered.
6. a kind of intelligent robot, it is characterised in that the robot includes:
Input acquisition module, it is configured to obtain multi-modal input information;
Directive generation module, it is configured to the parsing multi-modal input information, the bottom of the multi-modal interaction output of generation correspondence
Machine is instructed;
Priority match module, it is configured to be the corresponding execution priority of the slave computer instructions match;
Instruction reorder module, its be configured to according to the execution priority current all slave computers not sent are instructed into
Row sequence;
Command output module, it is configured to be sequentially output institute according to the ranking results that all slave computers not sent are instructed
State slave computer instruction;
Slave computer, its slave computer instruction for being configured to perform the command output module output carries out corresponding multi-modal output.
7. robot according to claim 6, it is characterised in that the instruction reorder module includes:
Instruction set memory cell, its slave computer instruction for being configured to preserve instruction set and will be currently generated adds slave computer to refer to
Order collection, also, slave computer instruction is deleted from the instruction set after output priority highest slave computer is instructed;
Instruction set sequencing unit, it is configured to carry out prioritization to all of slave computer instruction in the instruction set.
8. robot according to claim 6, it is characterised in that the instruction reorder module is additionally configured to the execution
Based on priority, the implementing precondition that the generation time instructed according to the slave computer and the slave computer are instructed is arranged
Sequence, wherein:
In two slave computer instructions, when the instruction of one of slave computer is the implementing precondition of another slave computer instruction
When, will be come in forward sequence as the instruction of the slave computer of implementing precondition;
In two slave computer instructions in the absence of implementing precondition relation, when the execution priority is identical, according to institute
The sequencing for stating the slave computer instruction generation time is ranked up.
9. robot according to claim 6, it is characterised in that the priority match module includes:
Interactive information collecting unit, its interaction mode for being configured to determine according to the multi-modal input information current robot
And/or the interaction demand of user;
Priority determining unit, it is configured to the interaction mode and/or the interaction demand determines that the slave computer refers to
The execution priority of order.
10. robot according to claim 6, it is characterised in that the priority match module includes:
Priority list storage unit, default slave computer instructs corresponding execution priority rank during it is configured to preservation system
List;
Priority determining unit, it is configured to according to the execution priority levels list to slave computer instructions match correspondence
Execution priority.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611199607.2A CN106845625A (en) | 2016-12-22 | 2016-12-22 | A kind of interactive output intent and robot for robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611199607.2A CN106845625A (en) | 2016-12-22 | 2016-12-22 | A kind of interactive output intent and robot for robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106845625A true CN106845625A (en) | 2017-06-13 |
Family
ID=59135305
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611199607.2A Pending CN106845625A (en) | 2016-12-22 | 2016-12-22 | A kind of interactive output intent and robot for robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106845625A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107390537A (en) * | 2017-07-26 | 2017-11-24 | 上海与德通讯技术有限公司 | A kind for the treatment of method and apparatus based on multitask |
CN107414828A (en) * | 2017-07-26 | 2017-12-01 | 上海与德通讯技术有限公司 | A kind of pure language processing method and device based on multitask |
CN110450151A (en) * | 2019-04-30 | 2019-11-15 | 北京云迹科技有限公司 | The configuration method and device of customized behavior for robot |
CN110928247A (en) * | 2019-10-14 | 2020-03-27 | 梁剑 | Control priority analysis system of artificial robot |
CN113703844A (en) * | 2021-07-27 | 2021-11-26 | 厦门市思芯微科技有限公司 | Instruction issuing method, system and device and computer readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103226148A (en) * | 2012-01-29 | 2013-07-31 | 桂林欧博仪器技术有限公司 | Environment analysis apparatus |
CN104238712A (en) * | 2013-06-20 | 2014-12-24 | 希捷科技有限公司 | Distributed power conveying |
US8924976B2 (en) * | 2011-08-26 | 2014-12-30 | Knu-Industry Cooperation Foundation | Task scheduling method and apparatus |
CN104252335A (en) * | 2013-06-28 | 2014-12-31 | 国际商业机器公司 | Predictive fetching and decoding for selected return instructions |
CN105773619A (en) * | 2016-04-26 | 2016-07-20 | 北京光年无限科技有限公司 | Electronic control system used for realizing grabbing behavior of humanoid robot and humanoid robot |
CN105959751A (en) * | 2016-04-29 | 2016-09-21 | 镇江惠通电子有限公司 | Remote control terminal and control method thereof |
CN106003028A (en) * | 2016-06-12 | 2016-10-12 | 江苏工程职业技术学院 | Control system of pesticide spraying robot and control method |
-
2016
- 2016-12-22 CN CN201611199607.2A patent/CN106845625A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8924976B2 (en) * | 2011-08-26 | 2014-12-30 | Knu-Industry Cooperation Foundation | Task scheduling method and apparatus |
CN103226148A (en) * | 2012-01-29 | 2013-07-31 | 桂林欧博仪器技术有限公司 | Environment analysis apparatus |
CN104238712A (en) * | 2013-06-20 | 2014-12-24 | 希捷科技有限公司 | Distributed power conveying |
CN104252335A (en) * | 2013-06-28 | 2014-12-31 | 国际商业机器公司 | Predictive fetching and decoding for selected return instructions |
CN105773619A (en) * | 2016-04-26 | 2016-07-20 | 北京光年无限科技有限公司 | Electronic control system used for realizing grabbing behavior of humanoid robot and humanoid robot |
CN105959751A (en) * | 2016-04-29 | 2016-09-21 | 镇江惠通电子有限公司 | Remote control terminal and control method thereof |
CN106003028A (en) * | 2016-06-12 | 2016-10-12 | 江苏工程职业技术学院 | Control system of pesticide spraying robot and control method |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107390537A (en) * | 2017-07-26 | 2017-11-24 | 上海与德通讯技术有限公司 | A kind for the treatment of method and apparatus based on multitask |
CN107414828A (en) * | 2017-07-26 | 2017-12-01 | 上海与德通讯技术有限公司 | A kind of pure language processing method and device based on multitask |
CN110450151A (en) * | 2019-04-30 | 2019-11-15 | 北京云迹科技有限公司 | The configuration method and device of customized behavior for robot |
CN110928247A (en) * | 2019-10-14 | 2020-03-27 | 梁剑 | Control priority analysis system of artificial robot |
CN113703844A (en) * | 2021-07-27 | 2021-11-26 | 厦门市思芯微科技有限公司 | Instruction issuing method, system and device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106845625A (en) | A kind of interactive output intent and robot for robot | |
CN109951547B (en) | Transaction request parallel processing method, device, equipment and medium | |
CN110502340A (en) | A kind of resource dynamic regulation method, device, equipment and storage medium | |
CN102999385B (en) | Multiprocessor cooperative processing method in computing equipment | |
CN104461693B (en) | Virtual machine update method and system under a kind of desktop cloud computing environment | |
CN104866465A (en) | Sensitive text detection method and device | |
CN106033393A (en) | Method and system for testing application program, and mobile terminal | |
CN103631590B (en) | The edit methods of automatic test script | |
CN106528065B (en) | A kind of thread acquisition methods and equipment | |
CN105912387A (en) | Method and device for dispatching data processing operation | |
CN110196761A (en) | Delay task processing method and processing device | |
CN103761108A (en) | Method and device for achieving behavior tree | |
CN110516789A (en) | The processing method of instruction set, device and relevant device in convolutional network accelerator | |
CN111527501A (en) | Chip adaptation determining method and related product | |
CN111491202A (en) | Video publishing method, device, equipment and storage medium | |
CN106625674B (en) | A kind of command processing method and robot for robot | |
CN104881307B (en) | Download implementation method and device | |
CN106055404A (en) | Method and device for cleaning up background application programs | |
CN109871270B (en) | Scheduling scheme generation method and device | |
CN109327321A (en) | Network model business executes method, apparatus, SDN controller and readable storage medium storing program for executing | |
CN107222618A (en) | Terminal screenshotss method and device | |
CN103501247A (en) | Method and device for processing high concurrency request | |
CN111190711B (en) | BDD combined heuristic A search multi-robot task allocation method | |
CN104346380A (en) | Data sequencing method and system on basis of MapReduce model | |
CN106126342A (en) | Multiprogram operation method and operating system towards intelligent robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |
|
RJ01 | Rejection of invention patent application after publication |