DriveML Huawei Autonomous Vehicles Challenge Forum

Go back to competition Back to thread list Post in this thread

> Simulator throws exception "Assertion `initialLane == 0' failed" for more than zero social vehicles

Hello!

I am trying to simulate multiple social vehicles and all my experiments (included the provided rnn_example) are failing at some early point with the following:

traci.exceptions.FatalTraCIError: connection closed by SUMO
2019-11-06 09:31:58,162 INFO trial_runner.py:615 -- Attempting to recover trial state from last checkpoint.
(pid=14455) sumo: /build/sumo-tHynv2/sumo-1.2.0+dfsg1/src/microsim/lcmodels/MSLCM_LC2013.cpp:1905: static double MSLCM_LC2013::distanceAlongNextRoundabout(double, const MSLane*, const std::vector<MSLane*>&): Assertion `initialLane == 0' failed.

The whole output is:
2019-11-06 09:40:39,599 ERROR trial_runner.py:569 -- Error processing event.
Traceback (most recent call last):
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/tune/trial_runner.py", line 515, in _process_trial
result = self.trial_executor.fetch_result(trial)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/tune/ray_trial_executor.py", line 351, in fetch_result
result = ray.get(trial_future[0])
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/worker.py", line 2121, in get
raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(FatalTraCIError): ray_worker (pid=16644, host=elena-HP-Pavilion-Laptop-14-bf1xx)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/agents/trainer.py", line 418, in train
raise e
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/agents/trainer.py", line 407, in train
result = Trainable.train(self)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/tune/trainable.py", line 176, in train
result = self._train()
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/agents/trainer_template.py", line 129, in _train
fetches = self.optimizer.step()
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/optimizers/multi_gpu_optimizer.py", line 140, in step
self.num_envs_per_worker, self.train_batch_size)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/optimizers/rollout.py", line 29, in collect_samples
next_sample = ray_get_and_free(fut_sample)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/utils/memory.py", line 33, in ray_get_and_free
result = ray.get(object_ids)
ray.exceptions.RayTaskError(FatalTraCIError): ray_worker (pid=16643, host=elena-HP-Pavilion-Laptop-14-bf1xx)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/evaluation/rollout_worker.py", line 469, in sample
batches = [self.input_reader.next()]
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 56, in next
batches = [self.get_data()]
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 99, in get_data
item = next(self.rollout_provider)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/evaluation/sampler.py", line 340, in _env_runner
base_env.send_actions(actions_to_send)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/env/base_env.py", line 332, in send_actions
self.vector_env.vector_step(action_vector)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/ray/rllib/env/vector_env.py", line 110, in vector_step
obs, r, done, info = self.envs[i].step(actions[i])
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/gym_hiway/env/competition_env.py", line 139, in step
observation, reward, agent_dones = self._engine.step(action_msg)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/game_engine.py", line 53, in step
return self._step(action_msg)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/game_engine.py", line 89, in _step
sim.step_traffic(dt)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/bullet_simulation.py", line 173, in step_traffic
social_vehicle_state = self._traffic_sim.step(dt, agent_vehicle_states)
File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/sumo_traffic_simulation.py", line 181, in step
self._traci_conn.simulationStep(self._cumulative_sim_seconds)
File "/usr/share/sumo/tools/traci/connection.py", line 329, in simulationStep
result = self._sendExact()
File "/usr/share/sumo/tools/traci/connection.py", line 105, in _sendExact
raise FatalTraCIError("connection closed by SUMO")
traci.exceptions.FatalTraCIError: connection closed by SUMO
(pid=16643) sumo: /build/sumo-tHynv2/sumo-1.2.0+dfsg1/src/microsim/lcmodels/MSLCM_LC2013.cpp:1905: static double MSLCM_LC2013::distanceAlongNextRoundabout(double, const MSLane*, const std::vector<MSLane*>&): Assertion `initialLane == 0' failed.
(pid=16643) ERROR:GameEngine:Simulation crashed with exception.Attempting to cleanly shutdown.
(pid=16643) ERROR:GameEngine:connection closed by SUMO
(pid=16643) Traceback (most recent call last):
(pid=16643) File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/game_engine.py", line 53, in step
(pid=16643) return self._step(action_msg)
(pid=16643) File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/game_engine.py", line 89, in _step
(pid=16643) sim.step_traffic(dt)
(pid=16643) File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/bullet_simulation.py", line 173, in step_traffic
(pid=16643) social_vehicle_state = self._traffic_sim.step(dt, agent_vehicle_states)
(pid=16643) File "/home/elena/anaconda3/envs/huawei/lib/python3.7/site-packages/hiway/sumo_traffic_simulation.py", line 181, in step
(pid=16643) self._traci_conn.simulationStep(self._cumulative_sim_seconds)
(pid=16643) File "/usr/share/sumo/tools/traci/connection.py", line 329, in simulationStep
(pid=16643) result = self._sendExact()
(pid=16643) File "/usr/share/sumo/tools/traci/connection.py", line 105, in _sendExact
(pid=16643) raise FatalTraCIError("connection closed by SUMO")
(pid=16643) traci.exceptions.FatalTraCIError: connection closed by SUMO
(pid=16643) Step #0.00 (0ms ?*RT. ?UPS, TraCI: 268ms, vehicles TOT 0 ACT 0 BUF 0)
2019-11-06 09:40:39,612 INFO trial_runner.py:615 -- Attempting to recover trial state from last checkpoint.

Posted by: Team_29 @ Nov. 6, 2019, 9:44 a.m.

Which version of SUMO are you using? We found this error with older versions of SUMO but it should go away if you upgrade to SUMO 1.3.1.

Posted by: HuaweiUK @ Nov. 6, 2019, 10:06 a.m.

Indeed, I am using 1.2:

sumo:
Installed: 1.2.0+dfsg1-14~xenial
Candidate: 1.2.0+dfsg1-14~xenial
Version table:
*** 1.2.0+dfsg1-14~xenial 500
500 http://ppa.launchpad.net/sumo/stable/ubuntu xenial/main amd64 Packages
100 /var/lib/dpkg/status
0.25.0+dfsg1-2 500
500 http://gb.archive.ubuntu.com/ubuntu xenial/universe amd64 Packages

However, I am not sure how to upgrade it. Running "sudo apt-get install sumo=1.3.1" returns that version 1.3.1 for sumo was not found. I have also added the repository "ppa:/sumo/stable", but it does not have the latest version cause I am getting no upgrades when running apt-get update. I also tried to install it from the source file (https://sourceforge.net/projects/sumo/) and follow the instructions here https://sumo.dlr.de/docs/Installing/Linux_Build.html, but I am getting errors.

Perhaps there is an easy way to upgrade?

Posted by: Team_29 @ Nov. 6, 2019, 12:53 p.m.

Ah, installation from source worked. Looks like there's no exceptions now!

Thanks!

Posted by: Team_29 @ Nov. 6, 2019, 1:17 p.m.
Post in this thread