Technology Development for Army Unmanned Ground Vehicles (2002) / Chapter Skim
Currently Skimming:
4. Autonomous Behavior Technologies
4. Autonomous Behavior Technologies
Pages 42-71
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 42... ...
PERCEPTION The perception technologies discussed in this section include the sensors, computers, and software modules essential for the fundamental UGV capabilities of A to B mobility and situation awareness. The section describes the current state of the art, estimates the levels of technology readiness, identifies capability gaps, and recommends areas of research and development needed.
|
From page 43... ...
; to validate assumptions made by the global path planner prior to initiation of the
|
From page 44... ...
Actual system completed and "fight qualified" through test and demonstration 9. Actual system "fight proven" through successful mission operations Lowest level of technology readiness.
|
From page 45... ...
Driving performance more broadly, even on structured roads, is well below that of a human operator. There is little evidence that perception technology is capable of supporting cross-country traverses of tactical significance, at tactical speeds, in unknown terrain, and in all iThe tactical behaviors are assumed to also encompass the positioning of the UGV as required by the on-board mission packages (e.g., RSTA, obscurant generation, mine clearance, weapons)
|
From page 46... ...
Active camera control (active vision) is required for the urban environment because of the simultaneous need for wide fields of view and high resolution.
|
From page 47... ...
Essentially no research 47 has been done on the additional skills beyond road-following and obstacle avoidance required to enable driving behavior more generally. Off-Roacl Autonomous off-road navigation requires that the vehicle characterize the terrain as necessary to plan a safe path through it and detect and identify features that are required by tactical behaviors.
|
From page 48... ...
Movement was to take place under day, night, or limited visibility conditions. Table 4-3 refines the TRL criteria used to estimate technology readiness for perception technologies.
|
From page 49... ...
hNo obstacle detection capability demonstrated at 100 or 120 km/in. Note: TRL = technology readiness level; SV = stereo video; MV+R = monocular video plus radar; SFLIR = stereo forward looking infrared; MFLIR+R = monocular forward looking infrared plus radar; LADAR = laser detection and ranging.
|
From page 50... ...
Wingman Hunter-Killer Note: TRL = technology readiness level; SV = stereo video; MV+R = monocular video plus radar; SFLIR = stereo forward looking infrared; MFLIR+R = monocular forward looking infrared plus radar. TABLE 4-6 TRL Estimates for Example UGV Applications: Off-Road/Cross-Country Mobility Speed (km/h)
|
From page 51... ...
. One relative navigation technique for a communication network is to determine the relative position of each member of the network by ranging on the network communication signals.
|
From page 52... ...
It may be possible for the Wingman to range off of communications signals from the section leader to aid in determining its relative position compared to the section leader. Theoretically, near-autonomous mobility (point A to point B)
|
From page 53... ...
Because of the communications network inherent in the Hunter-Killer, relative navigation/geolocation of individual units can be performed by ranging on these communications signals. This will help to overcome the vulnerability of GPS/INS, on which UGV depends for navigation/geolocation, because in areas of GPS denial (e.g., urban environments)
|
From page 54... ...
Because no one navigation solution meets all conditions, several navigation techniques must be included in any UGV design. Probably both an absolute and a relative navigation technique will be necessary.
|
From page 55... ...
, relative navigation techniques (INS, dead-reckoning, relative position estimates based upon ranging on communication signals) , position estimates based upon perception, information received from other assets (including UAVs, pseudolites)
|
From page 56... ...
As demonstrated in Demo III, the state of the art in path planning for an individual UGV, such as the Donkey and Wingman examples, is estimated at TRL 5, because of limited testing in relevant environments. The technology readiness level of multiple UGV and UAV path planning is currently TRL 3 for multiple UGVs and TRL 1 for multiple UGVs and UAVs.
|
From page 57... ...
Mission Planning This section defines the scope of autonomous missionplanning technology. It describes the state of the art and estimates the levels of technology readiness.
|
From page 58... ...
Various aspects of the example missions will be executed by specific software developed for tactical behaviors and cooperative behaviors as discussed in the section on Behaviors and Skills. Technology Reacliness Estimate While the mission planning in Demo III was very good (possibly TRL 5)
|
From page 59... ...
Tactical Behaviors This section defines the scope of tactical behavior technology. It describes the state of the art, estimates technology readiness, and discusses capability gaps.
|
From page 60... ...
Finally, the UGV must be able to learn by adjusting its knowledge base of tactical behaviors as it experiences repeatable enemy actions or other learning events. The military knowledge base needed to support these behaviors is similar to those needed for mission planning, including tactics, techniques and procedures as defined in tactical fighting documents and SOPs; and information from unit operations orders, including friendly force structure, detailed mission execution instructions, control graphics, enemy information, logistics (e.g., when and where to refuel)
|
From page 61... ...
Definition of Cooperative Behaviors In the field of psychology the word "behavior" is defined as "the aggregate of observable responses of an organism to internal and external stimuli." In robotics, behavior is often used to describe the observable response of a single robot vehicle to internal and external stimuli. When multiple vehicles are involved, the terminology "cooperative behavior" is often used to describe the response of the group of vehicles to internal and external stimuli.
|
From page 62... ...
Other methods for controlling a group of vehicles range from distributed autonomy (Fukuda et al., 1998) to intelligent squad control and general purpose cooperative mission planning (Brumitt and Stentz, 1998~.
|
From page 63... ...
A chart similar to Figure 4-7 would help the Army to understand how such conditions might affect the leader-follower concept. Technology Reacliness The technology readiness level of basic leader-follower cooperative behavior, such as might be exhibited by the Donkey and Wingman examples, is already TRL 6, but cooperative robot behavior, such as needed by the HunterKiller is still in a state of infancy.
|
From page 64... ...
The budget requirements necessary to bring cooperative behaviors for multiple UGVs and UAVs up to a TRL 6 could be several million dollars, and the time horizon could be 10 to 15 years away. Salient Uncertainties There are many possible Army missions for which cooperative behavior will be important, including: TECHNOLOGY DEVELOPMENT FOR ARMY UNMANNED GROUND VEHICLES Perimeter surveillance · Facility reconnaissance · Plume localization · Distributed communication relays · Distributed target acquisition · Explosive ordnance detection and · Building a camera collage.
|
From page 65... ...
ing, including adaptive control. The committee considered · A playbook of cooperative behaviors needs to be "machine learning" to be synonymous with what is com tested and evaluated for their usefulness on real hard- monly called "soft computing." Several briefings used the ware.
|
From page 66... ...
To our knowledge artificial neural networks have not been used successfully for off-road navigation, probably because the highly unstructured nature of the off-road environment would make it very difficult to train the network to handle all possible likely scenarios. Fuzzy Control Fuzzy control is a design technique that is based upon mathematics concepts from fuzzy logic, which is an extension of classical logic, which in turn is based upon an extension of classical set theory.
|
From page 67... ...
Resource limitations are not relevant given the intensity and amount of attention given to machine-learning paradigms, particularly in academia. The foregoing provides the basis for the answer to Task Statement Question 4.a as it pertains to learning/adaptation.
|
From page 68... ...
For FCS the Army should focus on use of learning technologies to resolve A-to-B mobility issues and on adaptive learning algorithms to develop tactical behaviors. SUMMARY OF TECHNOLOGY READINESS Table 4-9 summarizes the technology readiness level assessments made in each of the preceding sections vis-a-vis the four example UGV systems defined in Chapter 2.
|
From page 69... ...
TABLE 4-10 C~iNty Gaps in Autonomous Bcb~ior Tcchnologics Degree of D1~cuh~sk Low Cam Is Technology Ins Somber Donkey W1ngm~ Hunter-~ller Pe~epU~n \~-B ~-~ A-~-B ~~- o Summon madness ~god~ms far -Us two-~ns1on~ moping ad 1~1~
|
From page 70... ...
views. Mission Behaviors and skills Tactical skills Cooperative robots Le arnin g/adaptation Basic nonlethal selfprotection if touched or compromised.
|
From page 71... ...
A UTONOMO US BEHA VI OR TECHNOLO GIES · Low Difficulty/Low Risk Single short-duration technological approach needed to be assured of a high probability of success · Medium Difficulty/Medium Risk Optimum technical approach not clearly defined; one or more technical approaches possible that must be explored to be assured of a high probability of success · High Difficulty/High Risk Multiple approaches possible with difficult engineering challenges; some 71 basic research may be necessary to define an approach that will lead to a high probability of success. Tables 4-9 and 4-10 provide the basis for answers to Task Statement Questions 3.d and 4.c.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.