Abstract: An autonomous pile driving system identifies using a pile plan map a target location to install a pile. The system autonomously navigates towards the target location. The system autonomously detects using an object sensor system an orientation and location of the pile located within a threshold distance of the system. The system autonomously positions a tool of the autonomous pile driving system based on the detected orientation and location of the pile. The system autonomously picks up the pile using the positioned tool of the autonomous pile driving system. The system autonomously positions the pile based on the target location. The system autonomously drives the pile into ground at the target location.

Abstract: A autonomous off-road vehicle (AOV) accesses a pile plan map indicating a plurality of locations in a geographic area at which piles are to be installed. The AOV selects a first location and a second location from the plurality of locations using the pile plan map. The AOV autonomously navigates to the first location. The AOV autonomously loads a first pile onto a driving tool of the AOV. The AOV autonomously drives the first pile into the ground at the first location using the driving tool. The AOV autonomously navigates to the second location. the AOV autonomously loads a second pile onto the driving tool. And the AOV autonomously drives the second pile into the ground at the second location using the driving tool.

Abstract: A pile plan map indicating a plurality of locations in a geographic area at which piles are to be installed is accessed. A first set of locations is identified from the plurality of locations and a first set of piles to be driven into the ground at the first set of locations using the pile plan map is identified. An order for driving the first set of piles into the ground is identified and a pile type for each of the first set of piles is identified. Basket assembly instructions are generated for assembling the first set of piles into a basket based on the identified order and the identified pile types. The first set of piles are assembled autonomously or manually into the basket based on the generated basket assembly instructions.

Abstract: An autonomous off-road vehicle (AOV) autonomously performs a pile driving operation by driving a pile into the ground at a location identified by a pile plan map. The AOV detects one or more attributes of the pile using one or more sensors during or after the pile driving operation. The AOV determines whether the one or more attributes of the pile exceed respective tolerance thresholds. The AOV performs a quality control action in response to determining that the one or more attributes of the pile exceed the respective tolerance thresholds. The one or more attributes include one or more of a location and an orientation of the pile, and the quality control action is performed in response to determining that the location or the orientation of the pile exceeds the respective tolerance threshold.

Abstract: A pile plan map indicating a plurality of locations in a geographic area at which piles are to be installed is accessed. A first set of locations is identified from the plurality of locations and a first set of piles to be driven into the ground at the first set of locations using the pile plan map is identified. An order for driving the first set of piles into the ground is identified and a pile type for each of the first set of piles is identified. Basket assembly instructions are generated for assembling the first set of piles into a basket based on the identified order and the identified pile types. The first set of piles are assembled autonomously or manually into the basket based on the generated basket assembly instructions.

Abstract: An autonomous off-road vehicle (AOV) autonomously performs a pile driving operation by driving a pile into the ground at a location identified by a pile plan map. The AOV detects one or more attributes of the pile using one or more sensors during or after the pile driving operation. The AOV determines whether the one or more attributes of the pile exceed respective tolerance thresholds. The AOV performs a quality control action in response to determining that the one or more attributes of the pile exceed the respective tolerance thresholds. The one or more attributes include one or more of a location and an orientation of the pile, and the quality control action is performed in response to determining that the location or the orientation of the pile exceeds the respective tolerance threshold.

Abstract: An autonomous pile driving system identifies using a pile plan map a target location to install a pile. The system autonomously navigates towards the target location. The system autonomously detects using an object sensor system an orientation and location of the pile located within a threshold distance of the system. The system autonomously positions a tool of the autonomous pile driving system based on the detected orientation and location of the pile. The system autonomously picks up the pile using the positioned tool of the autonomous pile driving system. The system autonomously positions the pile based on the target location. The system autonomously drives the pile into ground at the target location.

Abstract: An autonomous off-road vehicle (AOV) includes a vehicle body and a vehicle arm coupled to the vehicle body and including a set of prongs and a clamp extending outward from an end of the vehicle arm. A controller causes the vehicle arm to pick up a pile by: aligning the set of prongs with an end of the pile such that a first prong aligns with an opening on a first side of a web of the pile and a second prong aligns with a space on a second side of the web, inserting the set of prongs into the opening on the first side and the space on the second side, and compressing the clamp into an exterior surface of a flange of the pile such that the set of prongs are reciprocally compressed into an interior surface of the flange on either side of the web.

Abstract: An autonomous pile driving system comprises an arm of an autonomous offroad vehicle (AOV) configured to hold and drive a pile, a chute configured to stabilize the pile as the pile is being driven. The autonomous pile driving system further comprises a controller configured to identify a location in the geographic area where a pile is to be driven (e.g., installed) and position the chute at the location. The controller aligns the pile secured by the AOV with an opening of the chute and inserts the pile into the chute by actuating an arm (or other suitable component) of the AOV securing the pile.

Abstract: In some implementations, the EMV uses a calibration to inform autonomous control over the EMV. To calibrate an EMV, the system first selects a calibration action comprising a control signal for actuating a control surface of the EMV. Then, using a calibration model comprising a machine learning model trained based on one or more previous calibration actions taken by the EMV, the system predicts a response of the control surface to the control signal of the calibration action. After the EMV executes the control signal to perform the calibration action, the EMV system monitors the actual response of the control signal and uses that to update the calibration model based on a comparison between the predicted and monitored states of the control surface.

Abstract: An earth moving vehicle (EMV) autonomously performs an earth moving operation within a dig site. If the EMV determines that a state of the EMV or the dig site triggers a triggering condition associated with a pause in the autonomous behavior of the EMV, the EMV determines a risk associated with the state or triggering condition. If the risk is greater than a first threshold, the EMV continues the autonomous performance and notifies a remote operator that the triggering condition was triggered. If the risk is greater than the first threshold risk but less than a second threshold risk, the EMV is configured to operate in a default state before continuing and notifying the remote operator. If the risk is greater than the second threshold risk, the EMV notifies the remote operator of the state pauses the performance until feedback is received from the remote operator.

Abstract: An autonomous earth moving system can determine a desired state for a portion of the EMV including at least one control surface. Then the EMV selects a set of control signals for moving the portion of the EMV from the current state to the desired state using a machine learning model trained to generate control signals for moving the portion of the EMV to the desired state based on the current state. After the EMV executes the selected set of control signals, the system measures an updated state of the portion of the EMV. In some cases, this updated state of the EMV is used to iteratively update the machine learning model using an online learning process.

Abstract: An earth moving vehicle (EMV) autonomously performs an earth moving operation within a dig site. If the EMV determines that a state of the EMV or the dig site triggers a triggering condition associated with a pause in the autonomous behavior of the EMV, the EMV determines a risk associated with the state or triggering condition. If the risk is greater than a first threshold, the EMV continues the autonomous performance and notifies a remote operator that the triggering condition was triggered. If the risk is greater than the first threshold risk but less than a second threshold risk, the EMV is configured to operate in a default state before continuing and notifying the remote operator. If the risk is greater than the second threshold risk, the EMV notifies the remote operator of the state pauses the performance until feedback is received from the remote operator.

Abstract: An autonomous off-road vehicle (AOV) includes a vehicle body and a vehicle arm coupled to the vehicle body and including a set of prongs and a clamp extending outward from an end of the vehicle arm. A controller causes the vehicle arm to pick up a pile by: aligning the set of prongs with an end of the pile such that a first prong aligns with an opening on a first side of a web of the pile and a second prong aligns with a space on a second side of the web, inserting the set of prongs into the opening on the first side and the space on the second side, and compressing the clamp into an exterior surface of a flange of the pile such that the set of prongs are reciprocally compressed into an interior surface of the flange on either side of the web.

Abstract: In some implementations, the EMV uses a calibration to inform autonomous control over the EMV. To calibrate an EMV, the system first selects a calibration action comprising a control signal for actuating a control surface of the EMV. Then, using a calibration model comprising a machine learning model trained based on one or more previous calibration actions taken by the EMV, the system predicts a response of the control surface to the control signal of the calibration action. After the EMV executes the control signal to perform the calibration action, the EMV system monitors the actual response of the control signal and uses that to update the calibration model based on a comparison between the predicted and monitored states of the control surface.

Abstract: An autonomous earth moving system can determine a desired state for a portion of the EMV including at least one control surface. Then the EMV selects a set of control signals for moving the portion of the EMV from the current state to the desired state using a machine learning model trained to generate control signals for moving the portion of the EMV to the desired state based on the current state. After the EMV executes the selected set of control signals, the system measures an updated state of the portion of the EMV. In some cases, this updated state of the EMV is used to iteratively update the machine learning model using an online learning process.

Abstract: A pile plan map indicating a plurality of locations in a geographic area at which piles are to be installed is accessed. A first set of locations is identified from the plurality of locations and a first set of piles to be driven into the ground at the first set of locations using the pile plan map is identified. An order for driving the first set of piles into the ground is identified and a pile type for each of the first set of piles is identified. Basket assembly instructions are generated for assembling the first set of piles into a basket based on the identified order and the identified pile types. The first set of piles are assembled autonomously or manually into the basket based on the generated basket assembly instructions.

Abstract: An autonomous off-road vehicle (AOV) includes a vehicle body and a vehicle arm coupled to the vehicle body and including a set of prongs and a clamp extending outward from an end of the vehicle arm. A controller causes the vehicle arm to pick up a pile by: aligning the set of prongs with an end of the pile such that a first prong aligns with an opening on a first side of a web of the pile and a second prong aligns with a space on a second side of the web, inserting the set of prongs into the opening on the first side and the space on the second side, and compressing the clamp into an exterior surface of a flange of the pile such that the set of prongs are reciprocally compressed into an interior surface of the flange on either side of the web.

Abstract: An autonomous off-road vehicle (AOV) autonomously performs a pile driving operation by driving a pile into the ground at a location identified by a pile plan map. The AOV detects one or more attributes of the pile using one or more sensors during or after the pile driving operation. The AOV determines whether the one or more attributes of the pile exceed respective tolerance thresholds. The AOV performs a quality control action in response to determining that the one or more attributes of the pile exceed the respective tolerance thresholds. The one or more attributes include one or more of a location and an orientation of the pile, and the quality control action is performed in response to determining that the location or the orientation of the pile exceeds the respective tolerance threshold.

Abstract: A autonomous off-road vehicle (AOV) accesses a pile plan map indicating a plurality of locations in a geographic area at which piles are to be installed. The AOV selects a first location and a second location from the plurality of locations using the pile plan map. The AOV autonomously navigates to the first location. The AOV autonomously loads a first pile onto a driving tool of the AOV. The AOV autonomously drives the first pile into the ground at the first location using the driving tool. The AOV autonomously navigates to the second location. the AOV autonomously loads a second pile onto the driving tool. And the AOV autonomously drives the second pile into the ground at the second location using the driving tool.