WIP integrating Learning in evolution#84
Open
portaloffreedom wants to merge 50 commits intodevelopmentfrom
Open
WIP integrating Learning in evolution#84portaloffreedom wants to merge 50 commits intodevelopmentfrom
portaloffreedom wants to merge 50 commits intodevelopmentfrom
Conversation
Added compiled proto files (c++ and python)
and added reporter in hyperneat
…oat to double in protobuf robotstateslearning.proto.
- C++14 - removed old DifferentialCPG - reset robot position after evaluation - load best controller at the end of learning - better separated learner and controller when loading - fixed implicit conversion of negative integer into unsigned integer
the NN needs to be activated as many times as the network is deep
- Added AngleToTargetDetectorClass - Added camera to HW controller - added OpenCV dependency - added raspicam dependency
DaanZ
reviewed
May 13, 2020
DaanZ
left a comment
DaanZ
left a comment
There was a problem hiding this comment.
I am a bit worried that some of the changes will affect the way we do experiments in the future, and I am not sure how much of these changes will actually be reusable.
| : next_state(nullptr) | ||
| const DifferentialCPG::ControllerParams ¶ms, | ||
| const std::vector<std::shared_ptr<Actuator>> &actuators, | ||
| std::shared_ptr<AngleToTargetDetector> angle_to_target_sensor) |
There was a problem hiding this comment.
Does every future version need to specify these parameters?
| const NEAT::Genome &gen) | ||
| : next_state(nullptr) | ||
| const NEAT::Genome &gen, | ||
| std::shared_ptr<AngleToTargetDetector> angle_to_target_sensor) |
There was a problem hiding this comment.
Is this necessary for future experiments?
|
|
||
| double DifferentialCPG::output_function(double input) const | ||
| { | ||
| return this->output_signal_factor |
There was a problem hiding this comment.
Split up formula for better readability.
| message(WARNING "Using local Gazebo @ ${gazebo_DIR}") | ||
| else() | ||
| find_package(gazebo 9 REQUIRED) | ||
| find_package(gazebo 10 REQUIRED) |
| const std::vector<std::shared_ptr<Actuator>> &_actuators); | ||
| const DifferentialCPG::ControllerParams ¶ms, | ||
| const std::vector<std::shared_ptr<Actuator>> &_actuators, | ||
| std::shared_ptr<AngleToTargetDetector> angle_to_target_sensor = nullptr); |
| this->previous_position_.Reset(); | ||
| this->start_position_.Reset(); | ||
| this->locomotion_type = "directed"; // {directed, gait} | ||
| this->locomotion_type = "turing_left"; // {directed, gait} |
|
|
||
| ///////////////////////////////////////////////// | ||
| void Evaluator::Reset() | ||
| void Evaluator::reset() |
| std::cout << "Loading controller " << controller_type << " and learner " << learner << std::endl; | ||
| auto brain_sdf = _sdf->GetElement("rv:brain"); | ||
| auto controller_type = brain_sdf->GetElement("rv:controller")->GetAttribute("type")->GetAsString(); | ||
| auto learner_type = brain_sdf->GetElement("rv:learner")->GetAttribute("type")->GetAsString(); |
| { | ||
| auto currentTime = _info.simTime.Double() - initTime_; | ||
| const gz::common::Time current_time = _info.simTime - initTime_; | ||
| const double current_time_d = current_time.Double(); |
| evaluator->simulation_update(world_pose, current_time_d, delta_time); | ||
| } | ||
|
|
||
| if (brain_) |
- Continue run - Load best genome IMC: - Modularity from yaml - open-loop logging BO: - LHS initialization Evaluator: - Logging components of the fitnesses - Reset robot correctly with fitness Positionmotor: - Added possibility for motor input noise python_code: - Added yaml functionality for IMC plane.world: - Added realtime and camera #commented <!-- -->
- Continue run - Load best genome IMC: - Modularity from yaml - open-loop logging BO: - LHS initialization Evaluator: - Logging components of the fitnesses - Reset robot correctly with fitness Positionmotor: - Added possibility for motor input noise python_code: - Added yaml functionality for IMC plane.world: - Added realtime and camera #commented <!-- -->
- Continue run - Load best genome IMC: - Modularity from yaml - open-loop logging BO: - LHS initialization Evaluator: - Logging components of the fitnesses - Reset robot correctly with fitness Positionmotor: - Added possibility for motor input noise python_code: - Added yaml functionality for IMC plane.world: - Added realtime and camera #commented <!-- -->
- Continue run - Load best genome IMC: - Modularity from yaml - open-loop logging BO: - LHS initialization Evaluator: - Logging components of the fitnesses - Reset robot correctly with fitness Positionmotor: - Added possibility for motor input noise python_code: - Added yaml functionality for IMC plane.world: - Added realtime and camera #commented <!-- -->
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.